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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 55668
    Prev
    Next
    INDEX
    Explanations

    quin

    np_max-act · gemini-2.0-flash

    The neuron flags occurrences of the chemical name “isoquinoline” (and its extended derivatives, e.g. “isoquinoline-4-carbaldehyde”).

    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
    .chomp
    -0.06
     biết
    -0.06
    �
    -0.06
     onPostExecute
    -0.06
    рует
    -0.06
     shar
    -0.06
     то
    -0.06
    ancellable
    -0.06
     dbname
    -0.06
     serialization
    -0.06
    POSITIVE LOGITS
    _GU
    0.07
     ASP
    0.07
    _TOKEN
    0.06
     sockets
    0.06
     ##
    0.06
     joint
    0.06
    INK
    0.06
     HS
    0.06
    design
    0.06
     soluble
    0.06
    Activations Density 0.001%

    No Known Activations