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. 22-LLAMASCOPE-RES-131K
    6. 5516
    Prev
    Next
    INDEX
    Explanations

    prefatory phrases indicating purpose or intention

    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
    odash
    -0.07
    äºİ
    -0.06
    zyst
    -0.06
    morgan
    -0.06
    olutions
    -0.06
    ê³Ħ
    -0.06
    olin
    -0.06
     Fountain
    -0.06
    strar
    -0.06
     rencont
    -0.06
    POSITIVE LOGITS
    tant
    0.09
    rie
    0.08
    centage
    0.08
    óż
    0.07
    ra
    0.07
    ce
    0.07
    ìĦľëĬĶ
    0.07
    rit
    0.07
    ia
    0.07
    ant
    0.07
    Activations Density 0.006%

    No Known Activations