© 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. 118992
    Prev
    Next
    INDEX
    Explanations

    punctuation marks, specifically periods

    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
    interop
    -0.07
    infra
    -0.07
     Slo
    -0.06
    haven
    -0.06
     Stub
    -0.06
    .ser
    -0.06
    \Bridge
    -0.06
     fatt
    -0.06
     Knock
    -0.06
     ty
    -0.06
    POSITIVE LOGITS
    entiful
    0.06
    åıĹåΰ
    0.06
    ESA
    0.06
    _exempt
    0.06
    oger
    0.06
    ROUP
    0.06
    uster
    0.06
    edia
    0.06
    aat
    0.06
    polator
    0.06
    Activations Density 0.000%

    No Known Activations