© 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. 130300
    Prev
    Next
    INDEX
    Explanations

    words related to melting and heat

    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
    жив
    -0.07
    ascar
    -0.07
    dia
    -0.06
    lies
    -0.06
    /me
    -0.06
    ridor
    -0.06
    uale
    -0.06
     dialect
    -0.06
    aic
    -0.06
     hoá
    -0.06
    POSITIVE LOGITS
    -down
    0.08
    aine
    0.07
    away
    0.07
    bÃŃr
    0.07
    çĦ¶
    0.07
    zer
    0.07
    /free
    0.07
    aways
    0.07
    -away
    0.07
     into
    0.07
    Activations Density 0.006%

    No Known Activations