© 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. 5-LLAMASCOPE-RES-131K
    11. 126399
    Prev
    Next
    INDEX
    Explanations

    expressions of creativity and innovation

    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
    illon
    -0.08
    acher
    -0.07
    ajor
    -0.07
    eyer
    -0.07
    ikel
    -0.07
    quier
    -0.07
    able
    -0.07
    ahlen
    -0.07
    amm
    -0.07
    oya
    -0.06
    POSITIVE LOGITS
    uvo
    0.07
    CUS
    0.06
    ÑĤÑĢо
    0.06
    837
    0.06
    -syntax
    0.06
    onDelete
    0.06
    ÑıÑģÑĮ
    0.06
    inds
    0.06
     GAL
    0.06
    Ñĸдно
    0.06
    Activations Density 0.000%

    No Known Activations