© 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
    4. Resid Post - 131k
    5. 3-RESID-POST-AA
    6. 121673
    Prev
    Next
    INDEX
    Explanations

    hacking

    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_3/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    _dark
    -0.08
     IU
    -0.07
    VS
    -0.06
    DRV
    -0.06
    onz
    -0.06
    uj
    -0.06
     pigment
    -0.06
     Ces
    -0.06
     Colts
    -0.06
     reign
    -0.06
    POSITIVE LOGITS
     hacking
    0.22
     hacked
    0.16
    acking
    0.12
     √
    0.08
     NSLocalizedString
    0.08
     erle
    0.07
     fishing
    0.07
     hacks
    0.07
    acked
    0.07
     visited
    0.07
    Activations Density 0.003%

    No Known Activations