© 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. 56503
    Prev
    Next
    INDEX
    Explanations

    terms related to assessments, training, and cooperation in research contexts

    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
    stu
    -0.07
    acci
    -0.06
    .mass
    -0.06
     humans
    -0.06
    å§Ķåijĺä¼ļ
    -0.06
    pite
    -0.06
    PÅĻi
    -0.06
    ikat
    -0.06
    aney
    -0.06
     funnel
    -0.06
    POSITIVE LOGITS
     Training
    0.08
     bilateral
    0.08
     training
    0.08
    .training
    0.08
    ilateral
    0.08
    -training
    0.07
     bil
    0.07
    training
    0.07
    endl
    0.07
    Training
    0.07
    Activations Density 0.002%

    No Known Activations