© 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. 74830
    Prev
    Next
    INDEX
    Explanations

    terms related to intra- and inter-related concepts, particularly involving frameworks and structures

    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
     newcom
    -0.08
    жи
    -0.08
    scape
    -0.08
    reau
    -0.07
    utsch
    -0.07
    skyt
    -0.07
    leme
    -0.07
    vod
    -0.07
    icaret
    -0.07
     ì¶ľìŀ¥
    -0.07
    POSITIVE LOGITS
    ocular
    0.09
    787
    0.07
    -
    0.06
    /Internal
    0.06
     within
    0.06
    913
    0.06
    /out
    0.06
    achment
    0.06
     Dob
    0.06
    /post
    0.06
    Activations Density 0.004%

    No Known Activations