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. 15-RESID-POST-AA
    6. 112706
    Prev
    Next
    INDEX
    Explanations

    societal collapse preparation

    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_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     wolf
    -0.08
     комплек
    -0.07
     functional
    -0.06
     پرد
    -0.06
    -icon
    -0.06
     Purple
    -0.06
    .Template
    -0.06
     інститут
    -0.06
     httpClient
    -0.06
    Func
    -0.06
    POSITIVE LOGITS
     nostalg
    0.06
     vua
    0.06
     coordin
    0.06
    _MET
    0.06
     waitFor
    0.06
    -host
    0.06
    @testable
    0.06
    iliği
    0.06
    {@
    0.06
     vel
    0.06
    Activations Density 0.062%

    No Known Activations