© 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. 93469
    Prev
    Next
    INDEX
    Explanations

    references to significant sports metaphors and symbols

    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
     thanks
    -0.06
    ugg
    -0.06
     IGN
    -0.06
    ron
    -0.06
     Portrait
    -0.06
     elect
    -0.05
    bl
    -0.05
     by
    -0.05
     Explorer
    -0.05
    öl
    -0.05
    POSITIVE LOGITS
    IBUT
    0.08
    iband
    0.07
    .scalablytyped
    0.07
    /WebAPI
    0.07
    _marshall
    0.07
    FORMAT
    0.07
    hci
    0.07
    åį«
    0.07
    posure
    0.07
    -format
    0.07
    Activations Density 0.016%

    No Known Activations