© 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. 40584
    Prev
    Next
    INDEX
    Explanations

    elements related to reality television show details and episode summaries

    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
    uese
    -0.07
    лÑĥг
    -0.06
    öl
    -0.06
    ended
    -0.06
    finally
    -0.06
    oi
    -0.06
    anki
    -0.06
     handleMessage
    -0.06
    ifting
    -0.06
    hea
    -0.06
    POSITIVE LOGITS
     inaugural
    0.10
     initial
    0.10
     Initial
    0.10
    Initial
    0.10
     tomorrow
    0.09
     Prel
    0.09
    initial
    0.08
     preliminary
    0.08
    .Initial
    0.08
     INITIAL
    0.08
    Activations Density 0.004%

    No Known Activations