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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 9-LLAMASCOPE-RES-131K
    6. 96230
    Prev
    Next
    INDEX
    Explanations

    the word "only" to highlight exclusivity or limitation

    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
    137
    -0.06
    anche
    -0.06
    rai
    -0.06
    876
    -0.06
    usz
    -0.06
    imed
    -0.06
    Ïĥα
    -0.06
    atsu
    -0.06
       
    -0.06
    ptr
    -0.06
    POSITIVE LOGITS
    ÅĽcie
    0.07
    EDA
    0.07
     váºŃy
    0.07
    ãĥ©ãĥ³ãĥī
    0.07
    /all
    0.07
    OMB
    0.07
    ebek
    0.07
    withstanding
    0.07
    iero
    0.07
     olmak
    0.07
    Activations Density 0.010%

    No Known Activations