© 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. 41632
    Prev
    Next
    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash

    phrases related to the consequences and implications of actions, especially in a business or technical context.

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

    The neuron fires on verbs that describe a change of state or action (e.g. ruined, sold, slowed, added, change).

    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
    Supplier
    -0.06
    .circular
    -0.06
     plá
    -0.06
    <Integer
    -0.06
    antidad
    -0.06
    .Request
    -0.06
     florida
    -0.06
    .AUTO
    -0.06
    \Query
    -0.06
     ``
    -0.06
    POSITIVE LOGITS
     original
    0.07
     EW
    0.07
    ,,,
    0.07
     CPF
    0.06
    Vendor
    0.06
     Erk
    0.06
     آثار
    0.06
    plementary
    0.06
    annah
    0.06
    जह
    0.06
    Activations Density 0.378%

    No Known Activations