© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 78668
    Prev
    Next
    INDEX
    Explanations

    classifications and taxonomic details of plant species

    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
    _ABI
    -0.07
     DISCLAIM
    -0.07
    irá
    -0.07
    ìĹ
    -0.07
     anale
    -0.07
     mastur
    -0.06
     chua
    -0.06
    abin
    -0.06
    cce
    -0.06
    isté
    -0.06
    POSITIVE LOGITS
    orum
    0.07
     subs
    0.07
     cum
    0.07
     _
    0.06
    culus
    0.06
    adiens
    0.06
    ĥ½
    0.06
    ensi
    0.06
     recess
    0.06
     minus
    0.06
    Activations Density 0.007%

    No Known Activations