© 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. 56475
    Prev
    Next
    INDEX
    Explanations

    references to historical events and significant moments in community recognition

    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
     programme
    -0.09
    NZ
    -0.09
    uckland
    -0.09
     Canadian
    -0.08
     programmes
    -0.08
    erland
    -0.08
    isku
    -0.08
    Canadian
    -0.08
     Programme
    -0.08
     adverts
    -0.07
    POSITIVE LOGITS
     Labor
    0.07
    ajar
    0.07
    EOF
    0.07
     neighbors
    0.07
     ABC
    0.07
     afl
    0.07
     Bend
    0.07
     Behavior
    0.06
    adel
    0.06
     Marr
    0.06
    Activations Density 0.568%

    No Known Activations