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. 91412
    Prev
    Next
    INDEX
    Explanations

    Opinions and beliefs

    np_max-act · gemini-2.0-flash

    The neuron spotlights author’s meta‐comments or evaluative/discourse cues (e.g. “we are able,” “in our opinion,” “Possible applications,” “Long ago,” “In this work”).

    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
     Garner
    -0.07
    WISE
    -0.07
     economic
    -0.07
    along
    -0.06
     Panther
    -0.06
     Gods
    -0.06
     rg
    -0.06
    估
    -0.06
    PHY
    -0.06
     Fit
    -0.06
    POSITIVE LOGITS
     glUniform
    0.07
     Few
    0.07
    @register
    0.07
     serão
    0.06
    prix
    0.06
    ("")]↵
    0.06
    раг
    0.06
    важ
    0.06
    /disable
    0.06
     tela
    0.06
    Activations Density 0.047%

    No Known Activations