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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 31-LLAMASCOPE-RES-131K
    6. 44395
    Prev
    Next
    INDEX
    Explanations

    terms related to news reporting and press conferences

    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
    é«
    -0.08
     gsi
    -0.07
    skirts
    -0.07
    celik
    -0.06
    stell
    -0.06
    arch
    -0.06
    å±
    -0.06
    oria
    -0.06
    SKI
    -0.06
    ski
    -0.06
    POSITIVE LOGITS
     conference
    0.14
    conference
    0.12
     briefing
    0.12
     conferences
    0.10
     confer
    0.09
     Conference
    0.09
    Conference
    0.09
     конÑĦеÑĢен
    0.08
    oms
    0.08
     seminar
    0.07
    Activations Density 0.005%

    No Known Activations