© 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. 76917
    Prev
    Next
    INDEX
    Explanations

    descriptors and comparisons related to plant 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
    ripe
    -0.07
    indow
    -0.07
    467
    -0.06
    ssf
    -0.06
    orpor
    -0.06
    acos
    -0.06
    á»IJ
    -0.06
    387
    -0.06
    iaux
    -0.06
    uler
    -0.06
    POSITIVE LOGITS
    endid
    0.07
     Geh
    0.07
     igual
    0.07
    ëģ¼
    0.07
    EQUAL
    0.06
    sch
    0.06
    ãĤ
    0.06
     pÅĻiÄįemž
    0.06
    Aceptar
    0.06
     μη
    0.06
    Activations Density 0.008%

    No Known Activations