© 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. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 15-LLAMASCOPE-RES-131K
    6. 104030
    Prev
    Next
    INDEX
    Explanations

    phrases that encourage engagement and participation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Text fragments that directly instruct or encourage the reader to take specific actions, often using second-person pronouns and imperative verbs.

    eleuther_acts_top20 · claude-3-7-sonnet-20250219Triggered by @lu-christina
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    aska
    -0.07
    odem
    -0.07
    dden
    -0.07
     proximity
    -0.06
    plet
    -0.06
    odb
    -0.06
    _physical
    -0.06
    ODE
    -0.06
    avian
    -0.06
    uddle
    -0.06
    POSITIVE LOGITS
     Equals
    0.07
    nave
    0.07
     Pearce
    0.07
    vor
    0.07
    amage
    0.06
     док
    0.06
    ãĥŃãĤ°
    0.06
    agar
    0.06
     resource
    0.06
     Conn
    0.06
    Activations Density 0.026%

    No Known Activations