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. 32308
    Prev
    Next
    INDEX
    Explanations

    parades and processions

    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
    multipart
    -0.07
     pago
    -0.07
     rebate
    -0.06
     Seiten
    -0.06
    내기
    -0.06
    EEEE
    -0.06
    Capt
    -0.06
    audio
    -0.06
     Frame
    -0.06
    оу
    -0.06
    POSITIVE LOGITS
    適
    0.06
     condu
    0.06
     CNS
    0.06
    bam
    0.06
    ひ
    0.06
    STANCE
    0.06
    ,,
    0.06
     vl
    0.06
     makeup
    0.06
    �
    0.06
    Activations Density 0.076%

    No Known Activations