© 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. 71399
    Prev
    Next
    INDEX
    Explanations

    scientific concepts related to noise and its sources in various environments

    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
     consect
    -0.07
     consec
    -0.06
    intern
    -0.06
    523
    -0.06
     membership
    -0.06
     Bro
    -0.06
    ia
    -0.06
     –
    -0.06
    @
    -0.06
    bill
    -0.06
    POSITIVE LOGITS
     background
    0.09
     noise
    0.08
     contamination
    0.08
    -background
    0.08
    noise
    0.08
    ène
    0.08
     sources
    0.08
    background
    0.07
    ifacts
    0.07
     backgrounds
    0.07
    Activations Density 0.055%

    No Known Activations