© 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. 3318
    Prev
    Next
    INDEX
    Explanations

    terms related to materials and their management in a logistical context

    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
    inel
    -0.07
    él
    -0.07
    thing
    -0.06
    eny
    -0.06
    laus
    -0.06
    aho
    -0.06
    ylon
    -0.06
    -series
    -0.06
    ober
    -0.06
    eva
    -0.06
    POSITIVE LOGITS
     Tet
    0.07
    çĽĺ
    0.06
    ÑĢог
    0.06
    ORN
    0.06
     ïĤ
    0.06
     peripheral
    0.06
    ãĢ
    0.06
     Wooden
    0.06
     cond
    0.06
    (æĹ¥
    0.06
    Activations Density 0.000%

    No Known Activations