© 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. 55797
    Prev
    Next
    INDEX
    Explanations

    references to location-based entities and educational affiliations

    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
     cro
    -0.07
     é«
    -0.06
    ETA
    -0.06
     over
    -0.06
     Cro
    -0.06
    APH
    -0.06
    аÑĢ
    -0.05
    FIX
    -0.05
     off
    -0.05
    &
    -0.05
    POSITIVE LOGITS
     STDCALL
    0.08
    ;element
    0.07
    ysz
    0.07
    gnore
    0.07
     RuntimeObject
    0.07
    ahl
    0.07
    uth
    0.07
    ialized
    0.07
    isclosed
    0.07
    #ae
    0.07
    Activations Density 0.006%

    No Known Activations