© 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. 119580
    Prev
    Next
    INDEX
    Explanations

    code comments and documentation notes

    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
    aylight
    -0.08
    (Op
    -0.08
    ÄIJT
    -0.08
    ìĬ´
    -0.08
    âĢ¦↵↵↵
    -0.07
     ogl
    -0.07
    ÑģÑĤÑİ
    -0.07
     jich
    -0.07
    (PR
    -0.07
    729
    -0.07
    POSITIVE LOGITS
    0.08
    0.07
    0.07
    Âł
    0.06
    ollo
    0.06
    OperationException
    0.06
     ded
    0.06
    å±±å¸Ĥ
    0.05
    £i
    0.05
    0.05
    Activations Density 0.178%

    No Known Activations