© 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. 125898
    Prev
    Next
    INDEX
    Explanations

    references to scientific citations and numerical data

    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
    sti
    -0.07
    ansi
    -0.07
    oto
    -0.07
    200
    -0.06
    retty
    -0.06
    avaÅŁ
    -0.06
    resentation
    -0.06
    emi
    -0.06
    hoa
    -0.06
    orks
    -0.06
    POSITIVE LOGITS
     recently
    0.10
     Recently
    0.08
     recent
    0.08
    ãĤĩãģĨ
    0.08
    recent
    0.08
    Recently
    0.07
     upcoming
    0.07
     lately
    0.06
     forthcoming
    0.06
    _recent
    0.06
    Activations Density 0.026%

    No Known Activations