© 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. 77041
    Prev
    Next
    INDEX
    Explanations

    elements related to selection processes and the associated criteria or methods

    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
    _hosts
    -0.08
    nicos
    -0.07
    cid
    -0.07
    заб
    -0.07
    aight
    -0.07
    mouth
    -0.07
    addtogroup
    -0.07
    먹
    -0.06
    isque
    -0.06
    PÅĻed
    -0.06
    POSITIVE LOGITS
     search
    0.10
     Search
    0.09
     searching
    0.09
     searches
    0.08
     selection
    0.08
    Search
    0.08
    search
    0.08
     process
    0.08
     hiring
    0.08
    =search
    0.07
    Activations Density 0.017%

    No Known Activations