© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 94505
    Prev
    Next
    INDEX
    Explanations

    expressions of personal recommendations and experiences related to home inspections

    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
    chts
    -0.08
    ần
    -0.08
    ByVersion
    -0.07
    ght
    -0.07
    inem
    -0.07
    ivar
    -0.07
    ứng
    -0.07
    änder
    -0.07
    Unavailable
    -0.07
    μβ
    -0.07
    POSITIVE LOGITS
    ison
    0.06
     va
    0.06
     wnd
    0.06
    .BorderStyle
    0.06
    les
    0.06
    getto
    0.06
     vel
    0.06
    iles
    0.06
     minor
    0.05
    åł
    0.05
    Activations Density 0.021%

    No Known Activations