© 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. 40653
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "The" and its variations, likely indicating headlines or prominent phrases in texts

    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
    usercontent
    -0.07
    idine
    -0.07
    erus
    -0.07
    à¤¾à¤Ł
    -0.07
    leet
    -0.07
    quisite
    -0.07
    äge
    -0.07
    avel
    -0.06
    rael
    -0.06
    elsinki
    -0.06
    POSITIVE LOGITS
    odor
    0.08
    asso
    0.07
     views
    0.07
    oretical
    0.07
    ais
    0.07
    ÛĮÙĩ
    0.07
    aison
    0.06
    tz
    0.06
    adora
    0.06
    atre
    0.06
    Activations Density 0.008%

    No Known Activations