© 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. 40587
    Prev
    Next
    INDEX
    Explanations

    terms related to assessment and data collection processes

    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
    asso
    -0.07
    ãĥ¼ãĥł
    -0.07
    affles
    -0.07
    iges
    -0.06
    via
    -0.06
    abyrin
    -0.06
    kov
    -0.06
    utzer
    -0.06
    bru
    -0.06
    rien
    -0.06
    POSITIVE LOGITS
    Äįas
    0.07
    oproject
    0.07
    åľ³
    0.07
    çŃĭ
    0.07
    ÏĢÏĮ
    0.06
    ä¸ĬäºĨ
    0.06
    ovaly
    0.06
    ött
    0.06
    achu
    0.06
    arih
    0.06
    Activations Density 0.000%

    No Known Activations