© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 15-LLAMASCOPE-RES-131K
    6. 103758
    Prev
    Next
    INDEX
    Explanations

    references to "mean" in various contexts, particularly related to measurable values or averages

    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
    gate
    -0.08
    s
    -0.08
    gens
    -0.07
    ged
    -0.07
    gence
    -0.07
    gle
    -0.07
    g
    -0.07
    naments
    -0.07
    gel
    -0.07
    ivery
    -0.07
    POSITIVE LOGITS
    nest
    0.09
    ings
    0.08
    ish
    0.08
    est
    0.08
    lessly
    0.08
    ups
    0.07
    liness
    0.07
    iversary
    0.07
    iful
    0.07
    liest
    0.07
    Activations Density 0.010%

    No Known Activations