© 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
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 43301
    Prev
    Next
    INDEX
    Explanations

    .

    np_max-act · gemini-2.0-flash

    This neuron activates on Dockerfile instructions that copy dependency files or install packages (e.g., “COPY requirements.txt” and “pip install …”).

    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
    uk
    -0.07
    lexport
    -0.07
    stringValue
    -0.07
    erap
    -0.06
    anh
    -0.06
    ør
    -0.06
    _pop
    -0.06
    Ja
    -0.06
    av
    -0.06
    hk
    -0.06
    POSITIVE LOGITS
     différentes
    0.06
     injuries
    0.06
    .compress
    0.06
     proclamation
    0.06
    .hour
    0.06
     couldn
    0.06
    -feed
    0.06
     constit
    0.06
     revealed
    0.06
    MING
    0.06
    Activations Density 0.004%

    No Known Activations