© 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. 739
    Prev
    Next
    INDEX
    Explanations

    terms related to mathematical coefficients and matrices

    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
    flow
    -0.08
    ëį°
    -0.07
    elp
    -0.07
    fly
    -0.07
    ish
    -0.07
     trÃŃ
    -0.06
    ging
    -0.06
    coming
    -0.06
    imeo
    -0.06
    abil
    -0.06
    POSITIVE LOGITS
    icients
    0.13
    icient
    0.11
    OutOfRangeException
    0.09
    ICIENT
    0.08
    chants
    0.08
    nuts
    0.07
    iciente
    0.07
    URRENT
    0.07
    گذ
    0.07
    chia
    0.07
    Activations Density 0.026%

    No Known Activations