© 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. 125176
    Prev
    Next
    INDEX
    Explanations

    expressions, voice

    np_max-act · gemini-2.0-flash

    The neuron fires on the participle “dripping,” highlighting adverbial “-ing” descriptors like “dripping with” that modify a noun (e.g. “voice dripping with satisfaction”).

    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
     bilder
    -0.07
    ору
    -0.06
    ��
    -0.06
     ~/
    -0.06
     zkou
    -0.06
     Bout
    -0.06
    ąd
    -0.06
    stateParams
    -0.06
    vic
    -0.06
     Sud
    -0.05
    POSITIVE LOGITS
    iddet
    0.07
     disease
    0.07
     dripping
    0.07
    _own
    0.07
     hepat
    0.07
     beef
    0.07
     full
    0.06
    linked
    0.06
     versatility
    0.06
    flation
    0.06
    Activations Density 0.004%

    No Known Activations