© 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. 70971
    Prev
    Next
    INDEX
    Explanations

    references to numerical and statistical data

    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
    oretical
    -0.06
    ัวร
    -0.06
     spite
    -0.06
    stood
    -0.06
    بÙĦ
    -0.05
    ç·Ĵ
    -0.05
    PLEX
    -0.05
    éĢ¸
    -0.05
    IGNAL
    -0.05
    Ñģли
    -0.05
    POSITIVE LOGITS
    rschein
    0.08
    IVO
    0.07
    allet
    0.07
    osaur
    0.07
    æĽ¸é¤¨
    0.07
    yaw
    0.07
     shape
    0.06
     addCriterion
    0.06
    ottom
    0.06
    ISON
    0.06
    Activations Density 0.103%

    No Known Activations