© 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. 83096
    Prev
    Next
    INDEX
    Explanations

    references to database table operations or configurations

    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
    θÏħ
    -0.07
    ãĥ¼ãĥ¬
    -0.07
    ROSS
    -0.07
    æ
    -0.07
    adius
    -0.06
    梨
    -0.06
    tons
    -0.06
     é«
    -0.06
     ä¸ĸ
    -0.06
     Kons
    -0.06
    POSITIVE LOGITS
    orz
    0.06
     tablename
    0.06
    usion
    0.06
    Cmd
    0.06
    ahy
    0.05
    otech
    0.05
    cedure
    0.05
    ohn
    0.05
     PRI
    0.05
    yro
    0.05
    Activations Density 0.000%

    No Known Activations