© 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. 17-LLAMASCOPE-RES-131K
    6. 94184
    Prev
    Next
    INDEX
    Explanations

    comparative phrases and values in relation to healthcare and constraints

    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
    azzi
    -0.07
    ORMAT
    -0.07
    SError
    -0.06
    alink
    -0.06
    AZY
    -0.06
    clair
    -0.06
    UME
    -0.06
    Ñģим
    -0.06
    wen
    -0.06
     SN
    -0.06
    POSITIVE LOGITS
     ones
    0.08
     current
    0.08
     Ket
    0.07
    å½ĵåīį
    0.06
    current
    0.06
    consts
    0.06
     already
    0.06
     ours
    0.06
     originals
    0.06
    ismu
    0.06
    Activations Density 0.044%

    No Known Activations