© 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. 83189
    Prev
    Next
    INDEX
    Explanations

    phrases emphasizing totality or completeness

    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
     itself
    -0.07
     and
    -0.07
     all
    -0.06
    æīĢæľī
    -0.06
     often
    -0.06
     many
    -0.06
    and
    -0.06
    1
    -0.06
    acle
    -0.05
    POSITIVE LOGITS
    maal
    0.11
    uded
    0.10
    udes
    0.09
    ude
    0.09
    zych
    0.09
    anning
    0.09
    viso
    0.09
    omor
    0.08
    -fontawesome
    0.08
     Hoch
    0.08
    Activations Density 0.021%

    No Known Activations