© 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. 77599
    Prev
    Next
    INDEX
    Explanations

    themes related to conflict or struggle

    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
    uers
    -0.07
    orta
    -0.07
    ÑĨей
    -0.07
    /simple
    -0.07
    endon
    -0.07
    alles
    -0.07
    rak
    -0.07
    odash
    -0.06
    istencia
    -0.06
    utow
    -0.06
    POSITIVE LOGITS
    into
    0.09
    via
    0.09
     into
    0.08
     via
    0.08
     Into
    0.07
     INTO
    0.07
     depths
    0.07
     fold
    0.07
     fray
    0.07
     stride
    0.07
    Activations Density 0.105%

    No Known Activations