© 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. 61277
    Prev
    Next
    INDEX
    Explanations

    relationships of dependency and influence among various factors

    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
    isco
    -0.06
    asi
    -0.06
    FA
    -0.06
    vinc
    -0.06
    ark
    -0.06
     Tomb
    -0.06
     Turing
    -0.06
    fa
    -0.05
    chen
    -0.05
    ste
    -0.05
    POSITIVE LOGITS
     factors
    0.11
     Factors
    0.10
     whether
    0.09
    ahat
    0.09
    .scalablytyped
    0.08
     determined
    0.08
     determines
    0.08
    whether
    0.07
    Factors
    0.07
     depends
    0.07
    Activations Density 0.042%

    No Known Activations