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. 55177
    Prev
    Next
    INDEX
    Explanations

    included

    np_max-act · gemini-2.0-flash

    The neuron activates on the standard boilerplate mention that “a copy is included in the LICENSE file.”

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    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
    urrenc
    -0.06
     Geschichte
    -0.06
     conveyor
    -0.06
     Og
    -0.06
    ETY
    -0.06
     mixer
    -0.06
    succ
    -0.06
    onse
    -0.06
     discourse
    -0.06
     ves
    -0.06
    POSITIVE LOGITS
     ngOnDestroy
    0.07
    sport
    0.06
     Bison
    0.06
     onCreateViewHolder
    0.06
     prevent
    0.06
    legate
    0.06
    \Json
    0.06
    heat
    0.06
     Billy
    0.06
    就算
    0.06
    Activations Density 0.002%

    No Known Activations