© 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. 125781
    Prev
    Next
    INDEX
    Explanations

    references to risks and uncertainties associated with investing

    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
    ansi
    -0.08
    asper
    -0.06
     stacks
    -0.06
    StackSize
    -0.06
     Challenger
    -0.06
    TK
    -0.06
    PLIT
    -0.06
    INTERFACE
    -0.06
    urch
    -0.06
    ditor
    -0.06
    POSITIVE LOGITS
    ÏħÏĥ
    0.07
    owler
    0.07
    syn
    0.06
    may
    0.06
    _ORD
    0.06
    den
    0.06
     ves
    0.06
    Sector
    0.06
    ì§ij
    0.06
     Synthetic
    0.06
    Activations Density 0.013%

    No Known Activations