© 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. 73685
    Prev
    Next
    INDEX
    Explanations

    technical/scientific texts

    np_max-act · gemini-2.0-flash

    The neuron selectively activates on content‐heavy, often multi-syllabic verbs (e.g. “increase,” “making,” “crystallize,” “show,” “connected”) that denote change or relational processes.

    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
     implementing
    -0.07
    Kate
    -0.06
     mé
    -0.06
    James
    -0.06
     Max
    -0.06
     Kate
    -0.06
    AWS
    -0.06
     JWT
    -0.06
     bouncing
    -0.06
    入
    -0.06
    POSITIVE LOGITS
    .spacing
    0.08
    μβρίου
    0.07
    (KeyEvent
    0.07
    �
    0.07
     yerleştir
    0.06
     }),
    0.06
    ret
    0.06
    ิกา
    0.06
    nah
    0.06
    ­i
    0.06
    Activations Density 0.121%

    No Known Activations