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. 11483
    Prev
    Next
    INDEX
    Explanations

    the repetition of the word "comb" in various contexts

    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
    rine
    -0.08
    izedName
    -0.08
     strtoupper
    -0.08
    iesz
    -0.07
     ucwords
    -0.07
    rung
    -0.07
    rone
    -0.07
    ارÙĩ
    -0.07
    _Tis
    -0.07
    arkan
    -0.07
    POSITIVE LOGITS
    inator
    0.21
    iners
    0.10
    iner
    0.10
    ina
    0.09
    ing
    0.09
    inar
    0.09
    iator
    0.08
    obi
    0.08
    i
    0.08
    obox
    0.08
    Activations Density 0.005%

    No Known Activations