© 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. 55969
    Prev
    Next
    INDEX
    Explanations

    references to points and scores in competitive contexts

    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
    ober
    -0.09
    eness
    -0.08
    ãĥĥãĥĪ
    -0.07
    BOOT
    -0.07
    endor
    -0.07
    olley
    -0.07
    .rar
    -0.07
     iddi
    -0.07
    /catalog
    -0.07
    uien
    -0.07
    POSITIVE LOGITS
     behind
    0.07
    zl
    0.06
     per
    0.06
     ad
    0.06
     McMahon
    0.05
     Pir
    0.05
    _losses
    0.05
    alus
    0.05
     separating
    0.05
     loss
    0.05
    Activations Density 0.004%

    No Known Activations