© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 89740
    Prev
    Next
    INDEX
    Explanations

    methods or procedures

    np_max-act · gemini-2.0-flash

    technical terms related to molecular and structural analysis in scientific research.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    The neuron detects references to experimental methods or procedural steps (e.g. protocols, preparation, handling, techniques).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    یره
    -0.07
     тер
    -0.07
     完
    -0.07
    PasswordField
    -0.07
     locked
    -0.07
     ASF
    -0.06
    _rt
    -0.06
     бактер
    -0.06
    (Parameter
    -0.06
     BorderLayout
    -0.06
    POSITIVE LOGITS
     professional
    0.06
    privileged
    0.06
    bie
    0.06
     register
    0.06
    ITAL
    0.06
     muj
    0.06
    führ
    0.06
     amplifier
    0.06
     Hans
    0.06
    Interested
    0.06
    Activations Density 0.049%

    No Known Activations