© 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. 87202
    Prev
    Next
    INDEX
    Explanations

    terms related to classifications and types of collections or categories

    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
    zel
    -0.07
    	Copyright
    -0.07
    ritten
    -0.07
    rawn
    -0.06
    ilot
    -0.06
    Įĵ
    -0.06
    icast
    -0.06
    али
    -0.06
    anton
    -0.06
    оÑĪ
    -0.06
    POSITIVE LOGITS
     commonly
    0.09
     types
    0.07
     encountered
    0.07
     常
    0.07
     options
    0.07
    常
    0.07
    rtype
    0.07
     available
    0.07
    options
    0.06
    yles
    0.06
    Activations Density 0.036%

    No Known Activations