© 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. 84448
    Prev
    Next
    INDEX
    Explanations

    references to mountains and related geographic features

    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
    iras
    -0.08
    erez
    -0.07
    removeAttr
    -0.07
    sak
    -0.06
    intree
    -0.06
    translator
    -0.06
     Tropical
    -0.06
    еÑĢж
    -0.06
     iface
    -0.06
    WebpackPlugin
    -0.06
    POSITIVE LOGITS
    ide
    0.08
     Dew
    0.07
    bine
    0.07
    side
    0.07
    ous
    0.07
    .dw
    0.07
    URRED
    0.07
    ides
    0.07
    -top
    0.07
    stead
    0.07
    Activations Density 0.018%

    No Known Activations