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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT
    7. Resid Post - 131k
    9. 27-RESID-POST-AA
    11. 100651
    Prev
    Next
    INDEX
    Explanations

    from

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_27/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.27.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     electric
    -0.06
    TabIndex
    -0.06
     negative
    -0.06
    -0.06
    　　 　 　
    -0.06
     climate
    -0.06
     HID
    -0.06
    ertil
    -0.06
     Bid
    -0.06
    イ
    -0.06
    POSITIVE LOGITS
     from
    0.25
     From
    0.19
    From
    0.16
    from
    0.16
     FROM
    0.14
    	from
    0.14
    —from
    0.13
    _from
    0.12
    FROM
    0.12
    -from
    0.11
    Activations Density 0.280%

    No Known Activations