© 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. 76284
    Prev
    Next
    INDEX
    Explanations

    references to professional affiliations and career milestones

    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
    owie
    -0.07
    .Slf
    -0.07
     Knife
    -0.07
    regor
    -0.07
    ãĥ¬ãĥ³
    -0.07
    memberof
    -0.06
    stoff
    -0.06
    ieve
    -0.06
    ilogue
    -0.06
    Knife
    -0.06
    POSITIVE LOGITS
     Gill
    0.07
    pole
    0.06
     Norman
    0.06
     sys
    0.06
    563
    0.06
    920
    0.06
    474
    0.06
     its
    0.06
    egra
    0.06
    CHAN
    0.05
    Activations Density 0.010%

    No Known Activations