© 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 (Instruct)
    4. Resid Post - 131k
    5. 7-RESID-POST-AA
    6. 108673
    Prev
    Next
    INDEX
    Explanations

    Days and dates

    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
     Damon
    -0.07
    enido
    -0.06
     cumulative
    -0.06
    *I
    -0.06
     minValue
    -0.06
     müzik
    -0.06
     �
    -0.06
     HMS
    -0.06
     AFP
    -0.06
    istique
    -0.06
    POSITIVE LOGITS
    (PRO
    0.07
     Scripture
    0.07
    .Features
    0.07
     discover
    0.06
    /projects
    0.06
     skilled
    0.06
    ")){↵
    0.06
     roofing
    0.06
     collar
    0.06
     शर
    0.06
    Activations Density 0.004%

    No Known Activations