© 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. 55754
    Prev
    Next
    INDEX
    Explanations

    comparisons and evaluations of quality or effectiveness

    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
    511
    -0.08
    æ´¥
    -0.06
    ales
    -0.06
    innacle
    -0.06
    filtr
    -0.06
    OffsetTable
    -0.06
    κά
    -0.06
     Dise
    -0.06
     branch
    -0.06
    alo
    -0.06
    POSITIVE LOGITS
     alike
    0.09
     Equal
    0.07
     equal
    0.07
    iju
    0.07
    yles
    0.07
    ispecies
    0.07
    Equal
    0.07
    reesome
    0.06
    .eql
    0.06
    uhe
    0.06
    Activations Density 0.004%

    No Known Activations