© 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. 125507
    Prev
    Next
    INDEX
    Explanations

    formatting symbols or slashes related to specific data structures

    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
    alog
    -0.06
    oron
    -0.06
    stan
    -0.06
    raries
    -0.06
     regime
    -0.06
    Ĥ
    -0.05
    Reuse
    -0.05
    itage
    -0.05
     XS
    -0.05
    hape
    -0.05
    POSITIVE LOGITS
    PR
    0.07
    /goto
    0.07
     nackte
    0.07
    наÑħ
    0.07
    prav
    0.07
    apan
    0.07
     Jah
    0.06
     press
    0.06
    IRON
    0.06
    appable
    0.06
    Activations Density 0.002%

    No Known Activations