© 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. 17-LLAMASCOPE-RES-131K
    11. 76202
    Prev
    Next
    INDEX
    Explanations

    comparative phrases involving numerical data

    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
    _geometry
    -0.07
    _DLL
    -0.06
    amp
    -0.06
    getManager
    -0.06
     Quint
    -0.06
     Cre
    -0.06
    éĹľ
    -0.06
     wÅĤa
    -0.06
    /process
    -0.06
     Hein
    -0.06
    POSITIVE LOGITS
     what
    0.08
    -minded
    0.07
    Pooling
    0.07
    vida
    0.07
     previous
    0.07
    ItemSelected
    0.07
     globe
    0.07
     recent
    0.06
    lic
    0.06
    ffen
    0.06
    Activations Density 0.018%

    No Known Activations