© 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. 40614
    Prev
    Next
    INDEX
    Explanations

    terms related to browser functionality and interaction

    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
    elpers
    -0.07
    ãĥ³ãĥĩ
    -0.07
    ange
    -0.06
    stre
    -0.06
    ija
    -0.06
    cri
    -0.06
    inel
    -0.06
    andon
    -0.06
    alm
    -0.06
    iano
    -0.06
    POSITIVE LOGITS
    TouchUpInside
    0.07
    _AES
    0.07
    pur
    0.07
    pig
    0.06
    rzy
    0.06
    립
    0.06
    ritis
    0.06
    å½ķ
    0.06
    Úĺ
    0.06
    isko
    0.06
    Activations Density 0.001%

    No Known Activations