© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 78309
    Prev
    Next
    INDEX
    Explanations

    questions beginning with "How."

    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
    regor
    -0.08
    ÑıÑĤелÑĮ
    -0.08
     æ®
    -0.07
    mojom
    -0.07
    殿
    -0.07
    ÏĩÏĮ
    -0.07
    ิยม
    -0.07
    ajor
    -0.07
    ruta
    -0.07
    sik
    -0.07
    POSITIVE LOGITS
    orth
    0.06
    boa
    0.06
    äng
    0.06
    147
    0.06
    hook
    0.05
    amed
    0.05
    oriously
    0.05
    tel
    0.05
    ób
    0.05
    y
    0.05
    Activations Density 0.005%

    No Known Activations