© 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. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 125972
    Prev
    Next
    INDEX
    Explanations

    elements related to numerical data or statistics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    abbo
    -0.06
    imbus
    -0.06
    ieder
    -0.06
    toPromise
    -0.06
     Victory
    -0.06
    igsaw
    -0.06
    thes
    -0.06
    rá
    -0.06
    umbo
    -0.06
    arkan
    -0.06
    POSITIVE LOGITS
    /generated
    0.07
    ãĤ¢ãĥ¼
    0.07
    ëģ¼
    0.07
     scrut
    0.06
    ule
    0.06
    exe
    0.06
    çĽijåIJ¬é¡µéĿ¢
    0.06
    loha
    0.06
    -floating
    0.06
    MOTE
    0.06
    Activations Density 0.000%

    No Known Activations