Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 31-LLAMASCOPE-RES-131K
    6. 43603
    Prev
    Next
    INDEX
    Explanations

    instances of the word "vanish" and related concepts of disappearing or ceasing to exist

    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
    ish
    -0.10
    itter
    -0.07
    dpi
    -0.07
    dle
    -0.07
    ered
    -0.06
    lein
    -0.06
    orage
    -0.06
    radu
    -0.06
    å°¼äºļ
    -0.06
    ictory
    -0.06
    POSITIVE LOGITS
    ishes
    0.14
    isses
    0.08
    si
    0.08
    ises
    0.08
    isse
    0.07
    ishing
    0.07
    van
    0.07
    is
    0.07
    iah
    0.07
    isNull
    0.06
    Activations Density 0.005%

    No Known Activations