© 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 EvalsExportsinterp-engineNEWAPI 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. 54674
    Prev
    Next
    INDEX
    Explanations

    terms related to solidity and strong physical characteristics

    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
    esis
    -0.09
    es
    -0.08
    ohl
    -0.07
    onder
    -0.07
    etic
    -0.07
    fulness
    -0.07
    athers
    -0.07
    ees
    -0.07
    DP
    -0.07
    ESIS
    -0.06
    POSITIVE LOGITS
    arity
    0.13
    ified
    0.10
    -solid
    0.10
    ifying
    0.09
    ness
    0.08
    ify
    0.08
    vice
    0.07
    -state
    0.07
    ly
    0.07
    çĦ¶
    0.07
    Activations Density 0.010%

    No Known Activations