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. 43901
    Prev
    Next
    INDEX
    Explanations

    instances of the word "with" or variations of showing connection and context

    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
    åĩ
    -0.07
    KHR
    -0.07
    ROME
    -0.07
    CKER
    -0.06
     prostitutas
    -0.06
    crest
    -0.06
     fruition
    -0.06
     ÑģÑħод
    -0.06
    291
    -0.06
    e
    -0.06
    POSITIVE LOGITS
    yr
    0.15
    yp
    0.14
    yc
    0.13
    sk
    0.13
    yt
    0.12
    ypad
    0.12
    raz
    0.12
    ype
    0.12
    zb
    0.12
    ted
    0.12
    Activations Density 0.004%

    No Known Activations