© 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. 22-LLAMASCOPE-RES-131K
    11. 4209
    Prev
    Next
    INDEX
    Explanations

    specific names and actions associated with organizations and individuals in formal contexts

    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
    ekli
    -0.07
    ahoo
    -0.06
    emen
    -0.06
    imes
    -0.06
     <",
    -0.06
     oppon
    -0.06
    į
    -0.06
     ÅŁer
    -0.06
    abbo
    -0.06
    ëŀ¨
    -0.06
    POSITIVE LOGITS
     Chronicle
    0.07
    asl
    0.06
    astle
    0.06
    Narr
    0.05
    arcy
    0.05
    wich
    0.05
    wechat
    0.05
    .async
    0.05
     sinus
    0.05
    asn
    0.05
    Activations Density 0.001%

    No Known Activations