© 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. 57163
    Prev
    Next
    INDEX
    Explanations

    themes related to violence and aggression

    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
    orta
    -0.08
    oret
    -0.07
    ona
    -0.06
    ertain
    -0.06
    ätt
    -0.06
     initial
    -0.06
    ici
    -0.06
    undler
    -0.06
    \Schema
    -0.06
    egis
    -0.06
    POSITIVE LOGITS
     rival
    0.08
    Ïĩο
    0.07
     randomly
    0.06
    hoot
    0.06
    มาà¸ģมาย
    0.06
     ucz
    0.06
    ournal
    0.06
     babies
    0.06
     thousands
    0.06
    é§
    0.06
    Activations Density 0.018%

    No Known Activations