© 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. 94133
    Prev
    Next
    INDEX
    Explanations

    words and phrases that indicate contrast or contradiction in arguments

    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
     ActionTypes
    -0.09
    podob
    -0.08
    imson
    -0.08
    ạm
    -0.08
    ìĽĥ
    -0.08
    ÏĥοÏħ
    -0.08
    sez
    -0.07
    ÏĢλ
    -0.07
    obar
    -0.07
    ÑĸйÑģ
    -0.07
    POSITIVE LOGITS
     there
    0.09
     it
    0.08
    ↵
    0.08
     they
    0.08
    forth
    0.07
    there
    0.07
    ;
    0.07
    they
    0.06
     we
    0.06
    645
    0.06
    Activations Density 0.029%

    No Known Activations