© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 78760
    Prev
    Next
    INDEX
    Explanations

    formatted comments and functions related to date and time

    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
    ennen
    -0.07
    zion
    -0.07
    егоÑĢ
    -0.07
    idis
    -0.06
    ngine
    -0.06
    ctor
    -0.06
    lander
    -0.06
    mite
    -0.06
    ctors
    -0.06
    agini
    -0.06
    POSITIVE LOGITS
     public
    0.10
    public
    0.09
    	public
    0.07
    .ix
    0.07
    ZO
    0.07
    .sap
    0.07
    .SingleOrDefault
    0.06
    trad
    0.06
     private
    0.06
    612
    0.06
    Activations Density 0.013%

    No Known Activations