© 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. 800
    Prev
    Next
    INDEX
    Explanations

    technical terms related to storage systems and data management

    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
    avra
    -0.07
    _EXEC
    -0.07
    outil
    -0.07
    reich
    -0.07
    cmc
    -0.06
     OSD
    -0.06
    flip
    -0.06
    indexed
    -0.06
    phan
    -0.06
    _DIP
    -0.06
    POSITIVE LOGITS
    _emit
    0.08
     unspecified
    0.07
    äter
    0.06
    32
    0.06
    ancel
    0.06
    еÑĨ
    0.06
    TreeView
    0.06
    onis
    0.06
    veau
    0.06
    edImage
    0.06
    Activations Density 0.002%

    No Known Activations