© 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. 9-LLAMASCOPE-RES-131K
    11. 95672
    Prev
    Next
    INDEX
    Explanations

    expressions related to exceptional effort and service

    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
     yg
    -0.07
    lap
    -0.06
    firm
    -0.06
    ossal
    -0.06
    itta
    -0.06
     Nug
    -0.06
    _iface
    -0.06
    oggles
    -0.06
    castle
    -0.06
     Nä
    -0.06
    POSITIVE LOGITS
    Ñī
    0.07
    undred
    0.07
    óng
    0.06
    ìłģìľ¼ë¡ľ
    0.06
    ãĥ¶
    0.06
    inite
    0.06
    enson
    0.06
    ÑĸнÑĮ
    0.06
    ikt
    0.06
    Insn
    0.06
    Activations Density 0.003%

    No Known Activations