© 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. 17-LLAMASCOPE-RES-131K
    6. 84453
    Prev
    Next
    INDEX
    Explanations

    terms related to rankings and ratings

    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
    ÑĮко
    -0.08
    ordin
    -0.08
    atik
    -0.07
    rena
    -0.07
    s
    -0.07
    eck
    -0.07
    acht
    -0.06
    anger
    -0.06
    aklı
    -0.06
    ektor
    -0.06
    POSITIVE LOGITS
    ings
    0.10
    erd
    0.10
    ered
    0.09
    furt
    0.09
    edList
    0.08
    enstein
    0.08
    lings
    0.08
    arel
    0.07
    ling
    0.07
    erb
    0.07
    Activations Density 0.010%

    No Known Activations