© 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. 87119
    Prev
    Next
    INDEX
    Explanations

    phrases indicating the provision of information or services

    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
    er
    -0.06
     Kirk
    -0.06
    214
    -0.06
    idon
    -0.05
    rador
    -0.05
    vester
    -0.05
    aterno
    -0.05
    ileo
    -0.05
    796
    -0.05
     ÄijÃłi
    -0.05
    POSITIVE LOGITS
    /Branch
    0.07
    _TP
    0.07
    azon
    0.07
     Lager
    0.07
    oya
    0.07
    onomous
    0.07
    _interfaces
    0.06
    wig
    0.06
    otes
    0.06
    ç£
    0.06
    Activations Density 0.014%

    No Known Activations