© 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. 126300
    Prev
    Next
    INDEX
    Explanations

    patterns or measurements of quantities in a numerical context

    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
    жд
    -0.07
    asto
    -0.07
    _Tis
    -0.07
    unga
    -0.07
    .AnchorStyles
    -0.07
    argo
    -0.07
    INDER
    -0.07
    вано
    -0.07
    ROUT
    -0.06
    deÅŁ
    -0.06
    POSITIVE LOGITS
    lon
    0.06
    iw
    0.06
    nul
    0.05
     Kings
    0.05
    æ±ł
    0.05
    еÑĤÑĭ
    0.05
    and
    0.05
    iy
    0.05
     sleep
    0.05
    -g
    0.05
    Activations Density 0.002%

    No Known Activations