© 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. 90362
    Prev
    Next
    INDEX
    Explanations

    abstract concepts and the process of thinking

    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
    gi
    -0.06
     Terrace
    -0.06
     igual
    -0.06
    serrat
    -0.06
    337
    -0.06
     Äijòi
    -0.06
     Household
    -0.06
     precis
    -0.06
    ROUGH
    -0.06
    ugal
    -0.06
    POSITIVE LOGITS
    others
    0.09
    Others
    0.08
     abstract
    0.08
     Others
    0.08
     distant
    0.08
     å¤ĸéĥ¨
    0.07
     others
    0.07
     OTHER
    0.07
    abstract
    0.07
    åĭĻ
    0.07
    Activations Density 0.026%

    No Known Activations