Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 60975
    Prev
    Next
    INDEX
    Explanations

    references to time intervals and game conditions

    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
     näch
    -0.09
    _NEXT
    -0.09
    _next
    -0.08
     onNext
    -0.08
     next
    -0.08
    _CONTINUE
    -0.07
     à¤ħà¤Ĺल
    -0.07
    lesen
    -0.07
    NEXT
    -0.07
    next
    -0.07
    POSITIVE LOGITS
     of
    0.07
     syndrome
    0.06
     Syndrome
    0.06
     tail
    0.06
     sequence
    0.06
     Sequence
    0.06
    endo
    0.06
    ycop
    0.06
    ado
    0.06
    of
    0.05
    Activations Density 0.022%

    No Known Activations