Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 7-RESID-POST-AA
    6. 78528
    Prev
    Next
    INDEX
    Explanations

    return

    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_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Chapel
    -0.07
     arom
    -0.06
     этим
    -0.06
     نمی
    -0.06
    Services
    -0.06
    _yaml
    -0.06
    τερ
    -0.06
    aneous
    -0.05
     spor
    -0.05
    投注
    -0.05
    POSITIVE LOGITS
    inclu
    0.07
     Submitted
    0.07
    abez
    0.07
    _dy
    0.07
     NVIDIA
    0.07
     ソ
    0.06
    daemon
    0.06
     bern
    0.06
    (DEFAULT
    0.06
    ैय
    0.06
    Activations Density 0.006%

    No Known Activations