© 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. 8894
    Prev
    Next
    INDEX
    Explanations

    logical reasoning

    np_max-act · gemini-2.0-flash

    This neuron activates on occurrences of the root “entail” (e.g. entail, entailed, entailment).

    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
    Timeline
    -0.07
     mower
    -0.06
    ึง
    -0.06
    ordered
    -0.06
     δεδο
    -0.06
    baru
    -0.06
     Swipe
    -0.06
    _resume
    -0.06
    BufferData
    -0.06
    andi
    -0.06
    POSITIVE LOGITS
     инвести
    0.07
     εγκα
    0.07
    	puts
    0.07
    (start
    0.06
    _not
    0.06
    wave
    0.06
    	trigger
    0.06
    _MIN
    0.06
     relic
    0.06
    (tmp
    0.06
    Activations Density 0.010%

    No Known Activations