© 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. 74683
    Prev
    Next
    INDEX
    Explanations

    various forms of the symbol for special characters or punctuation

    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
    aks
    -0.06
    118
    -0.06
    aurus
    -0.06
    2
    -0.06
    1
    -0.06
    isson
    -0.06
    ook
    -0.05
    inning
    -0.05
    cura
    -0.05
     Hale
    -0.05
    POSITIVE LOGITS
    plx
    0.08
    oyer
    0.07
    ept
    0.07
    nika
    0.07
    VertexBuffer
    0.07
    Ymd
    0.07
    mites
    0.07
    foy
    0.07
    á»Ń
    0.07
    mî
    0.07
    Activations Density 0.001%

    No Known Activations