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. 11-RESID-POST-AA
    6. 35449
    Prev
    Next
    INDEX
    Explanations

    Auxiliary verbs

    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
     If
    -0.08
     Since
    -0.07
     since
    -0.07
    арам
    -0.06
    If
    -0.06
     ©
    -0.06
     отнош
    -0.06
    rese
    -0.06
    Since
    -0.06
    562
    -0.06
    POSITIVE LOGITS
     when
    0.07
     getClient
    0.07
     RPM
    0.06
    ;display
    0.06
     ambulance
    0.06
    _USB
    0.06
    eee
    0.06
    devices
    0.06
    *******
    0.06
    (company
    0.06
    Activations Density 0.212%

    No Known Activations