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. 29103
    Prev
    Next
    INDEX
    Explanations

    mathematical notation or citations in a technical context

    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
    eee
    -0.08
    lore
    -0.08
    UFF
    -0.07
    ycl
    -0.07
    ibox
    -0.07
    ìĬ¤íģ¬
    -0.07
    ábado
    -0.07
    å±Ĭ
    -0.07
    ultimate
    -0.07
    umas
    -0.07
    POSITIVE LOGITS
     etc
    0.08
     literature
    0.06
    etc
    0.06
     cul
    0.06
    (iOS
    0.06
    rios
    0.06
    thon
    0.06
    uitka
    0.06
    ispens
    0.06
    Decode
    0.05
    Activations Density 0.018%

    No Known Activations