© 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. 5-LLAMASCOPE-RES-131K
    11. 126063
    Prev
    Next
    INDEX
    Explanations

    coding functions related to selection 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
    ogue
    -0.06
    éli
    -0.06
    ioned
    -0.06
     Mild
    -0.06
    ,
    -0.06
    ht
    -0.06
    clid
    -0.05
     ch
    -0.05
    -0.05
    nd
    -0.05
    POSITIVE LOGITS
    worthy
    0.08
    #echo
    0.07
    çī©
    0.07
    èªł
    0.07
    ifu
    0.07
    rons
    0.07
    isbury
    0.07
    hift
    0.07
    anter
    0.07
    ebi
    0.07
    Activations Density 0.001%

    No Known Activations