© 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. 55874
    Prev
    Next
    INDEX
    Explanations

    statements asserting factual accuracy or truth

    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
     Karlov
    -0.07
    lot
    -0.07
    laz
    -0.07
    æ¿ĥ
    -0.07
    latin
    -0.07
    ानत
    -0.07
    _principal
    -0.06
    ãĥªãĤ«
    -0.06
    ÑĢад
    -0.06
    naments
    -0.06
    POSITIVE LOGITS
    /false
    0.09
    ãĥ¼ãĥĩ
    0.07
    642
    0.06
    474
    0.06
    ayer
    0.06
     true
    0.06
    True
    0.06
    cased
    0.06
    .true
    0.06
    iesen
    0.06
    Activations Density 0.014%

    No Known Activations