Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 58
    Prev
    Next
    INDEX
    Explanations

    message

    np_max-act · gemini-2.0-flash

    The neuron fires on Spanish network‐communication wording—words like “comunica,” “enviar,” “mensajes,” “texto” and “a través” describing sending text messages over TCP.

    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
    ["@
    -0.07
    abstractmethod
    -0.07
     отношения
    -0.07
    olatile
    -0.06
    emacs
    -0.06
    _ZONE
    -0.06
     condemnation
    -0.06
    .FormBorderStyle
    -0.06
    bate
    -0.06
    engage
    -0.06
    POSITIVE LOGITS
    荷
    0.07
     cinsel
    0.07
     vyh
    0.07
     triangular
    0.06
     yelling
    0.06
    Flash
    0.06
     nxt
    0.06
     {},↵
    0.06
     thinner
    0.06
     Finnish
    0.06
    Activations Density 0.023%

    No Known Activations