© 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
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 92396
    Prev
    Next
    INDEX
    Explanations

    code, data

    np_max-act · gemini-2.0-flash

    The neuron never actually fires (all activations are zero), i.e. it isn’t matching any pattern. It currently finds nothing.

    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
                                                ↵
    -0.06
    OLVE
    -0.06
     혼
    -0.06
                                                    ↵
    -0.06
     Wie
    -0.06
    $m
    -0.06
     Sparse
    -0.06
     ""
    -0.06
     unf
    -0.06
    "In
    -0.06
    POSITIVE LOGITS
     vt
    0.06
    =device
    0.06
    زة
    0.06
     conna
    0.06
    .assertEqual
    0.06
     hilarious
    0.06
    .figure
    0.06
     quotient
    0.06
    -paced
    0.06
    -setting
    0.06
    Activations Density 0.080%

    No Known Activations