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. 56190
    Prev
    Next
    INDEX
    Explanations

    phrases that reference contrasts or dualities

    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
    ARGIN
    -0.07
    ToLocal
    -0.07
    gons
    -0.06
     mop
    -0.06
    obe
    -0.06
    hind
    -0.06
    ardash
    -0.06
    indr
    -0.06
    ContextHolder
    -0.06
    elif
    -0.06
    POSITIVE LOGITS
    /out
    0.11
    528
    0.08
    /down
    0.07
    /on
    0.07
    -between
    0.07
     Between
    0.07
    Between
    0.06
    ikat
    0.06
     sexes
    0.06
    /back
    0.06
    Activations Density 0.004%

    No Known Activations