© 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. 84585
    Prev
    Next
    INDEX
    Explanations

    terms and phrases related to scientific classification and taxonomy

    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
    Å¡ak
    -0.07
    rive
    -0.07
    nivel
    -0.07
    gunakan
    -0.07
    ereotype
    -0.07
    bbing
    -0.07
    ::-
    -0.06
    iage
    -0.06
    azen
    -0.06
    urdy
    -0.06
    POSITIVE LOGITS
    iniz
    0.06
     bush
    0.06
    ingham
    0.06
    okens
    0.06
    ela
    0.06
    ÏĦοÏĤ
    0.06
    mani
    0.05
    /go
    0.05
    acz
    0.05
    lesc
    0.05
    Activations Density 0.015%

    No Known Activations