© 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. 125441
    Prev
    Next
    INDEX
    Explanations

    references to categorization and classification within the text

    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
    ikt
    -0.08
     ****************************************************************************
    -0.07
    yme
    -0.07
     TORT
    -0.07
    aign
    -0.07
    unds
    -0.06
    lij
    -0.06
    ลาà¸Ķ
    -0.06
    ôn
    -0.06
    uci
    -0.06
    POSITIVE LOGITS
    uhn
    0.07
    priv
    0.06
     (!((
    0.06
    Äįet
    0.06
     priv
    0.06
    ellan
    0.06
    377
    0.06
     thr
    0.06
    ISING
    0.06
    ehr
    0.06
    Activations Density 0.001%

    No Known Activations