© 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. 83931
    Prev
    Next
    INDEX
    Explanations

    comparisons and analogies between different concepts or entities

    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
    osta
    -0.07
    claimer
    -0.06
    emas
    -0.06
    slaught
    -0.06
    iw
    -0.06
    ché
    -0.06
    iyon
    -0.06
    elt
    -0.06
    AsString
    -0.06
    _dom
    -0.06
    POSITIVE LOGITS
     equivalent
    0.13
     equivalents
    0.11
     Equivalent
    0.11
     counterparts
    0.09
    Equivalent
    0.09
     counterpart
    0.08
    akin
    0.08
     comparable
    0.08
     equival
    0.08
    leÅŁ
    0.07
    Activations Density 0.026%

    No Known Activations