© 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. 83274
    Prev
    Next
    INDEX
    Explanations

    significant milestones and targets related to achievement or progress

    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
    IPS
    -0.07
    alles
    -0.07
    .GroupLayout
    -0.06
    rak
    -0.06
    erval
    -0.06
    osta
    -0.06
    avan
    -0.06
    istar
    -0.06
    afone
    -0.06
    eyen
    -0.06
    POSITIVE LOGITS
     conclusions
    0.09
     conclusion
    0.08
     heights
    0.08
     levels
    0.08
    ouri
    0.08
     fruition
    0.08
     reach
    0.07
     reaches
    0.07
     Reach
    0.07
    eras
    0.07
    Activations Density 0.047%

    No Known Activations