© 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. 88985
    Prev
    Next
    INDEX
    Explanations

    http

    np_max-act · gemini-2.0-flash

    The neuron activates on the appearance of explicit HTTP/HTTPS URLs (e.g. tokens like “http”, “https”, “://”).

    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
     enqueue
    -0.07
     공고
    -0.07
     zoals
    -0.07
     αυ
    -0.07
     gode
    -0.07
     Penguins
    -0.06
    )");↵↵
    -0.06
    )?;↵↵
    -0.06
     �
    -0.06
    のだろう
    -0.06
    POSITIVE LOGITS
     incarceration
    0.07
     persona
    0.06
     tore
    0.06
     exclusion
    0.06
     sovereignty
    0.06
    aces
    0.06
     appointments
    0.06
    Ent
    0.06
    ’ta
    0.06
    _FORMAT
    0.06
    Activations Density 0.011%

    No Known Activations