© 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. 22-LLAMASCOPE-RES-131K
    11. 4300
    Prev
    Next
    INDEX
    Explanations

    terms related to product reviews and evaluations

    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
    .coord
    -0.06
    imon
    -0.06
    rees
    -0.06
    207
    -0.06
    GV
    -0.06
    ãĥ¼ãĥĹ
    -0.06
    imonial
    -0.06
     Till
    -0.06
    stype
    -0.06
    yect
    -0.05
    POSITIVE LOGITS
    лини
    0.09
    inear
    0.08
    Å©
    0.07
    anzi
    0.07
     hust
    0.07
     fur
    0.07
    fur
    0.07
     addCriterion
    0.07
     INLINE
    0.06
    ewe
    0.06
    Activations Density 0.000%

    No Known Activations