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. 55152
    Prev
    Next
    INDEX
    Explanations

    immunogenicity

    np_max-act · gemini-2.0-flash

    This neuron detects the stem “immunogen-” (as in “immunogenicity,” “immunogenic,” etc.).

    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
    FilterWhere
    -0.06
     troubles
    -0.06
    144
    -0.06
     tat
    -0.06
     slave
    -0.06
     �
    -0.06
     review
    -0.06
     wall
    -0.06
    3
    -0.06
    _stat
    -0.06
    POSITIVE LOGITS
    ogenic
    0.16
    gen
    0.08
    ogens
    0.08
     Đồng
    0.08
    PosX
    0.08
    ربية
    0.07
    очный
    0.07
    genic
    0.07
     belg
    0.07
    ीन
    0.07
    Activations Density 0.006%

    No Known Activations