© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 57472
    Prev
    Next
    INDEX
    Explanations

    terms related to geological processes and alterations in the Earth's structure

    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
     dint
    -0.07
     chez
    -0.06
    fy
    -0.06
    stav
    -0.06
    rets
    -0.06
     PREFIX
    -0.06
    .nt
    -0.06
    (OS
    -0.06
     Pend
    -0.05
    raž
    -0.05
    POSITIVE LOGITS
    rogen
    0.08
     during
    0.07
    aram
    0.07
    imbus
    0.07
    .bunifuFlatButton
    0.07
    šek
    0.06
    .opend
    0.06
    oice
    0.06
     possibly
    0.06
    itarian
    0.06
    Activations Density 0.010%

    No Known Activations