© 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. 15-LLAMASCOPE-RES-131K
    6. 90151
    Prev
    Next
    INDEX
    Explanations

    numerical values and statistics

    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
    ImageContext
    -0.06
    ptest
    -0.06
    usal
    -0.06
    umar
    -0.06
     dest
    -0.06
    cona
    -0.06
    alm
    -0.05
    uitka
    -0.05
    erde
    -0.05
     Fran
    -0.05
    POSITIVE LOGITS
    .Reporting
    0.08
    .Ticks
    0.07
    oreach
    0.07
    नल
    0.07
    çĵ
    0.07
    оба
    0.07
     koc
    0.07
    _TAC
    0.07
    дон
    0.07
    çĢ
    0.07
    Activations Density 0.040%

    No Known Activations