© 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. 82520
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "come" and its variations

    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
     sting
    -0.07
    åĿĬ
    -0.07
     desar
    -0.06
    .maximum
    -0.06
     Pazar
    -0.06
    ÑĢÑĥÑĤ
    -0.06
    bookmark
    -0.06
    å°
    -0.06
    Ticks
    -0.06
     Miller
    -0.06
    POSITIVE LOGITS
    unas
    0.08
    zik
    0.07
    .tt
    0.07
    imir
    0.07
    ocs
    0.06
     Mech
    0.06
    LEM
    0.06
    OOM
    0.06
    implify
    0.06
     mech
    0.06
    Activations Density 0.027%

    No Known Activations