© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 29871
    Prev
    Next
    INDEX
    Explanations

    mentions of resources related to a specific context or subject

    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
    eba
    -0.09
    ê
    -0.09
    ross
    -0.08
    oby
    -0.08
    ew
    -0.07
    ãģĬãĤĬ
    -0.07
    la
    -0.07
    irt
    -0.07
    strand
    -0.07
    infeld
    -0.07
    POSITIVE LOGITS
    ful
    0.09
    ential
    0.08
    fulness
    0.08
    .getOwnProperty
    0.08
    grily
    0.08
    ive
    0.07
    ellers
    0.07
    ales
    0.07
    izedName
    0.07
    seau
    0.07
    Activations Density 0.020%

    No Known Activations