© 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. 16152
    Prev
    Next
    INDEX
    Explanations

    expressions that indicate the presence or assessment of various forms of identification and organization

    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
    gmt
    -0.09
     pÅĻitom
    -0.09
     thereby
    -0.08
    миÑĢ
    -0.08
    Ãłu
    -0.07
     thus
    -0.07
     ultimately
    -0.07
    onor
    -0.07
    kaar
    -0.07
     halde
    -0.07
    POSITIVE LOGITS
     another
    0.17
    another
    0.14
     Another
    0.12
    Another
    0.11
     ebenfalls
    0.11
    åı¦ä¸Ģ
    0.10
     otro
    0.10
     similar
    0.09
     otra
    0.09
     дÑĢÑĥгого
    0.08
    Activations Density 0.018%

    No Known Activations