© 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. 106844
    Prev
    Next
    INDEX
    Explanations

    names and terms associated with organizations, institutions, and their products or services

    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
    ixo
    -0.07
    gmail
    -0.06
    Authenticate
    -0.06
    inho
    -0.06
    ollar
    -0.06
     unle
    -0.06
    sett
    -0.06
     Bild
    -0.06
    cesso
    -0.06
     tato
    -0.06
    POSITIVE LOGITS
     receiving
    0.09
     receive
    0.08
     rece
    0.08
     RECE
    0.07
     receives
    0.07
    ardo
    0.07
     Rece
    0.07
     xếp
    0.07
     participate
    0.07
     Receive
    0.07
    Activations Density 0.044%

    No Known Activations