© 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. 71073
    Prev
    Next
    INDEX
    Explanations

    negative values or indicators of loss

    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
    agn
    -0.07
    igh
    -0.07
    idget
    -0.06
    ongan
    -0.05
     lob
    -0.05
    ailer
    -0.05
    isty
    -0.05
    â̦↵
    -0.05
    azz
    -0.05
    igs
    -0.05
    POSITIVE LOGITS
     jadx
    0.08
    ħn
    0.08
     ë¬
    0.08
    èĬ
    0.08
    LocalizedString
    0.07
    rnek
    0.07
     Telefon
    0.07
    erdale
    0.07
    vester
    0.07
    缣
    0.07
    Activations Density 0.000%

    No Known Activations