© 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. 15-LLAMASCOPE-RES-131K
    6. 104037
    Prev
    Next
    INDEX
    Explanations

    instances of the word "set" and its forms, indicating various aspects of establishing or arranging things

    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
    dera
    -0.08
    aden
    -0.07
    /from
    -0.07
    ầy
    -0.07
    ona
    -0.06
    hare
    -0.06
    abilities
    -0.06
    eten
    -0.06
    ummies
    -0.06
    idders
    -0.06
    POSITIVE LOGITS
    tle
    0.13
    elah
    0.10
     aside
    0.09
     forth
    0.09
    uptools
    0.08
    sockopt
    0.08
    -up
    0.07
    embre
    0.07
    aside
    0.07
     sail
    0.07
    Activations Density 0.028%

    No Known Activations