© 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 (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 125930
    Prev
    Next
    INDEX
    Explanations

    string

    np_max-act · gemini-2.0-flash

    The neuron flags identifiers that serve as function parameters of type string in Go code.

    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
     ASD
    -0.07
    ğü
    -0.06
    numpy
    -0.06
    _comparison
    -0.06
     planets
    -0.06
    _spacing
    -0.06
     excited
    -0.06
    (http
    -0.06
    ectomy
    -0.06
     holes
    -0.06
    POSITIVE LOGITS
    riday
    0.07
    wallet
    0.07
    ではなく
    0.06
    amera
    0.06
    StyleSheet
    0.06
     listBox
    0.06
    oce
    0.06
    _display
    0.06
     mayor
    0.06
    kening
    0.06
    Activations Density 0.002%

    No Known Activations