© 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
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT (Instruct)
    7. Resid Post - 131k
    9. 19-RESID-POST-AA
    11. 51930
    Prev
    Next
    INDEX
    Explanations

    thermal ablation

    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_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Works
    -0.07
    -frame
    -0.07
    _PLUS
    -0.07
     polish
    -0.06
    Orig
    -0.06
     наиболее
    -0.06
    бут
    -0.06
    。我
    -0.06
    Sharing
    -0.06
    Authority
    -0.06
    POSITIVE LOGITS
     loss
    0.06
     Shr
    0.06
     Mathf
    0.06
    modifiable
    0.06
     Administration
    0.06
    ково
    0.06
    stdcall
    0.06
     cellspacing
    0.06
     similarity
    0.06
     grips
    0.06
    Activations Density 0.035%

    No Known Activations