© 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. 767
    Prev
    Next
    INDEX
    Explanations

    have

    np_max-act · gemini-2.0-flash

    The neuron fires on very common short “function” words (high-frequency stopwords like on, the, to, have, 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
     důsled
    -0.06
    ensors
    -0.06
     hoc
    -0.06
     різних
    -0.05
    .Business
    -0.05
    Vy
    -0.05
     �
    -0.05
    sth
    -0.05
    玛
    -0.05
     limestone
    -0.05
    POSITIVE LOGITS
    _except
    0.07
     _↵↵
    0.07
    .done
    0.07
    ")↵↵↵
    0.06
     href
    0.06
    εω
    0.06
     wooded
    0.06
    ')}}↵
    0.06
    .React
    0.06
    uestion
    0.06
    Activations Density 0.144%

    No Known Activations