© 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 (Instruct)
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 125217
    Prev
    Next
    INDEX
    Explanations

    ino

    np_max-act · gemini-2.0-flash

    various organic chemical compounds used in industrial applications.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    This neuron fires on the “–amino–” fragment in chemical compound names (i.e. the “amino”/“ino” subtoken in molecules’ names).

    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
    Sat
    -0.07
     '<
    -0.06
    Cons
    -0.06
    _empresa
    -0.06
     Kill
    -0.06
    같
    -0.06
     users
    -0.06
    Нас
    -0.06
     Fox
    -0.06
    (rec
    -0.06
    POSITIVE LOGITS
    inou
    0.08
    amba
    0.08
    ampo
    0.07
     incomplete
    0.06
    urbation
    0.06
    amin
    0.06
    odial
    0.06
    νο
    0.06
    ิโน
    0.06
    _Invoke
    0.06
    Activations Density 0.014%

    No Known Activations