© 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. 15-LLAMASCOPE-RES-131K
    11. 61871
    Prev
    Next
    INDEX
    Explanations

    phrases related to giving back and community support

    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
    hl
    -0.07
    nee
    -0.06
    lob
    -0.06
    kaar
    -0.06
    .appendTo
    -0.06
    stav
    -0.06
    nul
    -0.06
    .misc
    -0.06
    kir
    -0.06
    abyrinth
    -0.06
    POSITIVE LOGITS
    /WebAPI
    0.07
    eward
    0.07
    alic
    0.07
     kepada
    0.07
    icha
    0.07
    mada
    0.06
    ë°Ľ
    0.06
     eldre
    0.06
    _CAN
    0.06
     Institutions
    0.06
    Activations Density 0.004%

    No Known Activations