© 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. 125387
    Prev
    Next
    INDEX
    Explanations

    words related to food and eating experiences

    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
    liness
    -0.09
    eel
    -0.08
    izable
    -0.08
    itä
    -0.08
    atisch
    -0.08
    (s
    -0.07
    izabeth
    -0.07
    anza
    -0.07
    isch
    -0.07
    à¥įस
    -0.07
    POSITIVE LOGITS
    (es
    0.22
    es
    0.18
    y
    0.14
    s
    0.12
    ES
    0.11
    esin
    0.10
    sing
    0.10
    'es
    0.10
    ses
    0.10
    ãĥ§
    0.10
    Activations Density 0.101%

    No Known Activations