© 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
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 92164
    Prev
    Next
    INDEX
    Explanations

    bury

    np_max-act · gemini-2.0-flash

    This neuron activates on tokens related to following or unfollowing someone (e.g., “follow,” “following,” “unfollow”).

    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
    Know
    -0.07
     berry
    -0.06
    parer
    -0.06
     Technical
    -0.06
     incorporates
    -0.06
    IED
    -0.06
     Earl
    -0.06
     knew
    -0.06
     earlier
    -0.06
    ICS
    -0.06
    POSITIVE LOGITS
     "'");↵
    0.07
     Gibraltar
    0.07
     Enumerator
    0.07
    (suite
    0.07
    >Delete
    0.07
    ataires
    0.07
    реб
    0.07
     сос
    0.06
     тоб
    0.06
    SubMenu
    0.06
    Activations Density 0.057%

    No Known Activations