© 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. 40613
    Prev
    Next
    INDEX
    Explanations

    punctuation marks and the articulation of casual speech

    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
    aska
    -0.08
    rador
    -0.07
     Kraj
    -0.07
     whereas
    -0.07
    iese
    -0.06
    lict
    -0.06
     kuru
    -0.06
    -www
    -0.06
    á»ijc
    -0.06
     coinc
    -0.06
    POSITIVE LOGITS
     Part
    0.10
     part
    0.09
    Part
    0.08
    _part
    0.07
     tear
    0.07
     Pt
    0.07
    {@
    0.07
     Tear
    0.07
    part
    0.06
     redux
    0.06
    Activations Density 0.036%

    No Known Activations