Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 90500
    Prev
    Next
    INDEX
    Explanations

    mass spectrometry

    np_max-act · gemini-2.0-flash

    The neuron fires on mentions of mass‐spectrometry techniques and related instrumentation terms.

    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
    (drop
    -0.07
    Plans
    -0.06
    ạ
    -0.06
    英文
    -0.06
    흥
    -0.06
     PSI
    -0.06
    DeviceInfo
    -0.06
    dns
    -0.06
    Stroke
    -0.05
    none
    -0.05
    POSITIVE LOGITS
     Ελλά
    0.07
     virtual
    0.07
    .extensions
    0.07
    -sem
    0.07
     retros
    0.06
    .gender
    0.06
    .rest
    0.06
     mö
    0.06
    ","",
    0.06
    .self
    0.06
    Activations Density 0.135%

    No Known Activations