© 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. 57109
    Prev
    Next
    INDEX
    Explanations

    structural definitions and layout specifications in code

    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
    ingu
    -0.08
    ?type
    -0.07
    íıIJ
    -0.07
     Wid
    -0.07
    lessly
    -0.07
    reu
    -0.07
    antor
    -0.07
     PROCUREMENT
    -0.06
    práv
    -0.06
    olini
    -0.06
    POSITIVE LOGITS
    à¹Ĩ
    0.06
    -t
    0.06
     central
    0.06
    央
    0.06
    owi
    0.06
    owy
    0.06
    mite
    0.06
    ende
    0.06
     pil
    0.06
    adius
    0.06
    Activations Density 0.001%

    No Known Activations