© 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. 15-LLAMASCOPE-RES-131K
    11. 104100
    Prev
    Next
    INDEX
    Explanations

    references to different levels or types of formulas

    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
    ening
    -0.08
    ened
    -0.08
    leigh
    -0.07
    oda
    -0.07
    551
    -0.07
    efa
    -0.07
    ensi
    -0.06
    aney
    -0.06
    UNE
    -0.06
    robe
    -0.06
    POSITIVE LOGITS
    ayout
    0.08
    e
    0.08
    ulario
    0.07
    ative
    0.07
    ssel
    0.07
    dehyde
    0.07
    ÑģÑĮ
    0.07
    ignum
    0.07
    tega
    0.07
    onitor
    0.07
    Activations Density 0.017%

    No Known Activations