© 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. 15-LLAMASCOPE-RES-131K
    6. 61946
    Prev
    Next
    INDEX
    Explanations

    structural elements of programming code or data annotations

    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
    blick
    -0.07
    ammad
    -0.07
    asons
    -0.07
    oppers
    -0.07
    arro
    -0.06
    verbs
    -0.06
    erif
    -0.06
    licants
    -0.06
    imd
    -0.06
    á»Ļi
    -0.06
    POSITIVE LOGITS
    971
    0.06
    ÑĸÑģно
    0.06
    287
    0.06
    /workspace
    0.06
    æ¸
    0.06
    wor
    0.06
    988
    0.06
    973
    0.06
    åºŃ
    0.06
     ÑģвÑı
    0.06
    Activations Density 0.001%

    No Known Activations