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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    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. 7-RESID-POST-AA
    6. 5141
    Prev
    Next
    INDEX
    Explanations

    observations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    .addr
    -0.06
    _package
    -0.06
    (key
    -0.06
     conquered
    -0.06
     smiled
    -0.06
     giant
    -0.06
     allerg
    -0.06
    .Return
    -0.06
     recipient
    -0.06
     purchasing
    -0.05
    POSITIVE LOGITS
     observation
    0.13
     observations
    0.12
    هایی
    0.07
     ضربه
    0.07
    often
    0.07
     uvědom
    0.07
     ICollection
    0.07
     simples
    0.07
     excessively
    0.07
     gözlem
    0.07
    Activations Density 0.010%

    No Known Activations