© 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. 106309
    Prev
    Next
    INDEX
    Explanations

    terms related to absorption and absorption processes

    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
    dling
    -0.08
    el
    -0.07
    biz
    -0.06
    ispers
    -0.06
    yll
    -0.06
    izia
    -0.06
    ifact
    -0.06
    alties
    -0.06
     Clifford
    -0.06
    atre
    -0.06
    POSITIVE LOGITS
    ption
    0.09
    ively
    0.08
    ptive
    0.08
    edImage
    0.08
    .twimg
    0.08
    SingleNode
    0.07
    OLUTE
    0.07
    orption
    0.07
    querque
    0.07
    PTION
    0.07
    Activations Density 0.011%

    No Known Activations