© 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. 22-LLAMASCOPE-RES-131K
    11. 4263
    Prev
    Next
    INDEX
    Explanations

    elements related to academic rigor and structural analysis

    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
    amik
    -0.07
    ubern
    -0.07
     æĬķ稿
    -0.06
     Asp
    -0.06
    onso
    -0.06
     Licht
    -0.06
    lander
    -0.06
    deb
    -0.06
    rex
    -0.06
    Interpreter
    -0.06
    POSITIVE LOGITS
     coverage
    0.10
    coverage
    0.10
    Coverage
    0.10
     Coverage
    0.10
     lect
    0.09
     ped
    0.08
    _coverage
    0.08
     motiv
    0.08
    Topics
    0.07
     students
    0.07
    Activations Density 0.018%

    No Known Activations