© 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. 15-LLAMASCOPE-RES-131K
    11. 26926
    Prev
    Next
    INDEX
    Explanations

    significant historical dates or numerical information related to events

    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
    @(
    -0.07
    ymbol
    -0.07
     dostan
    -0.06
     Kramer
    -0.06
     Gross
    -0.06
     th
    -0.06
    çĶ²
    -0.06
    ãĥ¼ãĥ³
    -0.06
    }elseif
    -0.06
    çīĻ
    -0.06
    POSITIVE LOGITS
    atre
    0.07
    OUNTER
    0.06
    ),
    0.06
    INDOW
    0.06
    acle
    0.06
    ateau
    0.06
    λικά
    0.06
    )
    0.06
    orton
    0.06
    *.
    0.06
    Activations Density 0.045%

    No Known Activations