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. 89009
    Prev
    Next
    INDEX
    Explanations

    primary

    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
     congen
    -0.07
     Mut
    -0.07
     Coil
    -0.07
    282
    -0.07
     Obt
    -0.07
     let
    -0.06
    oot
    -0.06
     Geological
    -0.06
     nec
    -0.06
     �
    -0.06
    POSITIVE LOGITS
     primary
    0.13
     Primary
    0.12
    Primary
    0.10
     primarily
    0.09
    .textLabel
    0.09
    .Primary
    0.09
    ار
    0.08
    :
    0.08
    ы
    0.08
    primary
    0.08
    Activations Density 0.020%

    No Known Activations