© 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. 76752
    Prev
    Next
    INDEX
    Explanations

    the word "without" in various contexts

    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
     ÑĩаÑģом
    -0.08
    aret
    -0.08
     вÑĢемен
    -0.08
    wipe
    -0.08
     nedir
    -0.08
    Ñģий
    -0.07
    egan
    -0.07
    ander
    -0.07
    EventArgs
    -0.07
    HEMA
    -0.07
    POSITIVE LOGITS
     regard
    0.15
     necessarily
    0.10
     being
    0.09
     any
    0.09
     regards
    0.08
     having
    0.08
    för
    0.08
    /out
    0.08
     much
    0.07
     ever
    0.07
    Activations Density 0.028%

    No Known Activations