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. 27-RESID-POST-AA
    6. 73248
    Prev
    Next
    INDEX
    Explanations

    DNA components

    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
     hlas
    -0.07
    ств
    -0.06
    nika
    -0.06
     informed
    -0.06
    _clause
    -0.06
     mest
    -0.06
    _decrypt
    -0.06
     doubled
    -0.06
    .ini
    -0.06
     vitae
    -0.06
    POSITIVE LOGITS
    -hard
    0.07
    }],↵
    0.06
     Earn
    0.06
     VIR
    0.06
    ีด
    0.06
    bx
    0.06
    ็กซ
    0.06
    �
    0.06
     PSI
    0.06
     respectable
    0.06
    Activations Density 0.021%

    No Known Activations