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. 8595
    Prev
    Next
    INDEX
    Explanations

    alpha

    np_max-act · gemini-2.0-flash

    The neuron activates on Greek‐letter–style subunit labels (e.g. “α” or “β” with numeric or decimal values).

    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
     několika
    -0.07
    Lines
    -0.07
    anten
    -0.06
     Threshold
    -0.06
    .average
    -0.06
     sideline
    -0.06
     imminent
    -0.06
    .Take
    -0.06
     contagious
    -0.06
     weeds
    -0.06
    POSITIVE LOGITS
     Betty
    0.06
    リカ
    0.06
    .z
    0.06
    ีเอ
    0.06
    責
    0.06
     peel
    0.06
    ":"
    0.06
    kj
    0.06
     vě
    0.06
    ②
    0.06
    Activations Density 0.009%

    No Known Activations