© 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 (Instruct)
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 55570
    Prev
    Next
    INDEX
    Explanations

    similarity

    np_max-act · gemini-2.0-flash

    This neuron fires on discourse markers that introduce comparisons or examples—words like “similar,” “like,” “something,” and “other.”

    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
    аш
    -0.07
    forward
    -0.07
    Floor
    -0.06
    -forward
    -0.06
    .Glide
    -0.06
     colored
    -0.06
    White
    -0.06
     foot
    -0.06
     forward
    -0.06
     STORY
    -0.06
    POSITIVE LOGITS
    'label
    0.07
    .Allow
    0.07
    "));
↵
↵
    0.07
     türlü
    0.06
     *);↵
    0.06
    )");
↵
    0.06
    .Compose
    0.06
     kara
    0.06
    "url
    0.06
    '];
↵
↵
    0.06
    Activations Density 0.006%

    No Known Activations