© 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
    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. 6748
    Prev
    Next
    INDEX
    Explanations

    societal systems

    np_max-act · gemini-2.0-flash

    The neuron detects explicit references to “political” contexts—i.e. occurrences of the word “political” (and closely related political-domain terms).

    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
    incorrect
    -0.07
     Doug
    -0.06
     violations
    -0.06
     Ron
    -0.06
    212
    -0.06
    cow
    -0.06
     Vac
    -0.06
     ----------------------------------------------------------------------------
    -0.06
    Logs
    -0.06
     accents
    -0.06
    POSITIVE LOGITS
    .extract
    0.07
     detach
    0.07
    .count
    0.07
    (store
    0.07
    ctica
    0.07
    ُل
    0.07
    Bu
    0.07
     Keeps
    0.06
    .checkBox
    0.06
     optarg
    0.06
    Activations Density 0.274%

    No Known Activations