© 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. 106056
    Prev
    Next
    INDEX
    Explanations

    numerical values and their relationships in contexts related to scores, statistics, or comparisons

    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
     slightly
    -0.07
    askell
    -0.06
    .eulerAngles
    -0.06
    mp
    -0.06
    kami
    -0.06
    ipi
    -0.06
     Always
    -0.06
     Cain
    -0.06
     slight
    -0.06
     plenty
    -0.06
    POSITIVE LOGITS
     only
    0.13
     remaining
    0.13
    åī©
    0.12
     ONLY
    0.11
    remaining
    0.11
    only
    0.10
     Remaining
    0.10
     entirely
    0.10
     reduced
    0.09
     virtually
    0.09
    Activations Density 0.048%

    No Known Activations