© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 82576
    Prev
    Next
    INDEX
    Explanations

    punctuation marks and specific grammatical elements within sentences

    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
    assa
    -0.07
    esome
    -0.07
    째
    -0.07
    ìĬµ
    -0.07
    uche
    -0.07
    ζα
    -0.07
    ogenerated
    -0.07
    egers
    -0.07
    ön
    -0.06
    館
    -0.06
    POSITIVE LOGITS
    .gov
    0.07
    chester
    0.07
     unto
    0.06
    ipi
    0.06
    andle
    0.06
    _errno
    0.06
     Coleman
    0.06
     tolerance
    0.06
     union
    0.05
    .tw
    0.05
    Activations Density 0.001%

    No Known Activations