Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 78346
    Prev
    Next
    INDEX
    Explanations

    occurrences of the term "Wo" or closely related 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
    unker
    -0.06
    allet
    -0.06
    949
    -0.06
    nge
    -0.06
    asa
    -0.06
    borg
    -0.06
    alore
    -0.06
    abile
    -0.06
     inaugural
    -0.06
    ouch
    -0.06
    POSITIVE LOGITS
    efully
    0.07
    fgang
    0.07
    Isl
    0.07
     Pros
    0.07
    ody
    0.07
    esty
    0.07
    czy
    0.06
    cie
    0.06
    sey
    0.06
    hani
    0.06
    Activations Density 0.010%

    No Known Activations