Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 106645
    Prev
    Next
    INDEX
    Explanations

    phrases related to physical positioning or posture

    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
    åķ
    -0.08
    crest
    -0.07
     Patch
    -0.07
     PATCH
    -0.07
    .MixedReality
    -0.07
     Sized
    -0.07
    plen
    -0.07
     táºŃp
    -0.07
    uche
    -0.07
    umar
    -0.07
    POSITIVE LOGITS
     Laud
    0.06
     pedal
    0.06
    elop
    0.06
     Dayton
    0.06
     Jess
    0.06
     sav
    0.06
    acies
    0.05
    273
    0.05
     Gad
    0.05
     whilst
    0.05
    Activations Density 0.007%

    No Known Activations