© 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. 29720
    Prev
    Next
    INDEX
    Explanations

    dates and time periods associated with events

    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
    μιÏĥ
    -0.08
    ingham
    -0.07
    297
    -0.07
    914
    -0.07
    hart
    -0.06
    /Branch
    -0.06
    hower
    -0.06
    ýš
    -0.06
    ãĥ³ãĥĶ
    -0.06
    .semantic
    -0.06
    POSITIVE LOGITS
     hết
    0.06
    åIJ§
    0.06
     end
    0.06
    LOC
    0.06
    isk
    0.06
    indre
    0.06
    ISK
    0.06
    ilate
    0.06
    ector
    0.06
    _warnings
    0.06
    Activations Density 0.023%

    No Known Activations