© 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. 93647
    Prev
    Next
    INDEX
    Explanations

    file path components and directory structures

    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
    isphere
    -0.07
    jang
    -0.07
     nÄĥ
    -0.07
     ç¯
    -0.07
    ality
    -0.07
    iveau
    -0.07
    astro
    -0.07
    æĥ
    -0.07
    наÑĤ
    -0.07
    zel
    -0.07
    POSITIVE LOGITS
     projects
    0.08
    Projects
    0.08
     Projects
    0.07
    -working
    0.07
    projects
    0.07
    _projects
    0.06
     work
    0.06
    _working
    0.06
    062
    0.06
     Project
    0.06
    Activations Density 0.005%

    No Known Activations