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. 11-RESID-POST-AA
    6. 122567
    Prev
    Next
    INDEX
    Explanations

    the, your

    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_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    raith
    -0.07
     novice
    -0.06
     groups
    -0.06
     seasonal
    -0.06
     trabaj
    -0.06
    pretty
    -0.06
    #ifndef
    -0.06
    mach
    -0.06
     Neuroscience
    -0.06
     shark
    -0.06
    POSITIVE LOGITS
    %=
    0.07
     {_
    0.06
     inlet
    0.06
    序
    0.06
    	assertThat
    0.06
    (pass
    0.06
    .freq
    0.06
    \v
    0.06
    .names
    0.06
     ať
    0.06
    Activations Density 0.058%

    No Known Activations