© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 106683
    Prev
    Next
    INDEX
    Explanations

    speculative statements about the future

    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
     capsule
    -0.07
    eydi
    -0.07
    laz
    -0.06
    bor
    -0.06
    ImageContext
    -0.06
     Zur
    -0.06
    ileÅŁ
    -0.06
    yleft
    -0.06
    izu
    -0.06
    agy
    -0.06
    POSITIVE LOGITS
     power
    0.10
    power
    0.08
     energy
    0.08
    verter
    0.08
     electricity
    0.08
     Power
    0.07
     electric
    0.07
    ower
    0.07
     POWER
    0.07
    POWER
    0.07
    Activations Density 0.000%

    No Known Activations