Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 5-LLAMASCOPE-RES-131K
    6. 126322
    Prev
    Next
    INDEX
    Explanations

    event times and dates

    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
    iert
    -0.07
     rub
    -0.06
    262
    -0.06
     P
    -0.06
    eri
    -0.06
    io
    -0.06
    urst
    -0.06
    mai
    -0.05
    achi
    -0.05
    quote
    -0.05
    POSITIVE LOGITS
    CLUD
    0.07
    pei
    0.07
    олÑĮ
    0.07
    /ay
    0.07
    hausen
    0.07
    ARSER
    0.07
    ладÑĥ
    0.07
    Ä±ÅŁÄ±k
    0.07
     unf
    0.07
    ahren
    0.07
    Activations Density 0.010%

    No Known Activations