© 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. 94122
    Prev
    Next
    INDEX
    Explanations

    configuration option names in a technical 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
    ipt
    -0.07
    ber
    -0.07
    ower
    -0.07
    urence
    -0.06
    ina
    -0.06
    iden
    -0.06
    amer
    -0.06
    un
    -0.06
    igen
    -0.06
    SSIP
    -0.06
    POSITIVE LOGITS
    iaux
    0.07
    <typeof
    0.07
    olini
    0.06
    alles
    0.06
    ضÙĦ
    0.06
    ’s
    0.06
    oldt
    0.06
    λικ
    0.06
    mage
    0.06
    ỳ
    0.06
    Activations Density 0.003%

    No Known Activations