© 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. 126938
    Prev
    Next
    INDEX
    Explanations

    references and instructions related to documentation and payment processes

    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
    /wiki
    -0.06
    flux
    -0.06
    боÑĢа
    -0.06
    otre
    -0.06
    otto
    -0.06
    ulls
    -0.06
    _LD
    -0.06
    нак
    -0.05
    CP
    -0.05
    con
    -0.05
    POSITIVE LOGITS
     contained
    0.10
    contained
    0.10
     included
    0.10
    included
    0.09
    Contained
    0.08
    Included
    0.08
    ÏĮν
    0.08
     Included
    0.07
     INCLUDED
    0.07
     document
    0.07
    Activations Density 0.027%

    No Known Activations