© 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. 106468
    Prev
    Next
    INDEX
    Explanations

    various forms of the verb "approach."

    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
    assin
    -0.08
    uti
    -0.08
    op
    -0.07
    ogan
    -0.06
    keh
    -0.06
     Dawson
    -0.06
    eff
    -0.06
     States
    -0.06
    ÑģÑĭ
    -0.06
     pá
    -0.06
    POSITIVE LOGITS
    Playback
    0.08
    getSingleton
    0.07
    sing
    0.07
    /compiler
    0.07
    égor
    0.07
    vrier
    0.07
    OrElse
    0.07
    alim
    0.07
    --+
    0.07
    orsche
    0.06
    Activations Density 0.013%

    No Known Activations