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. 11539
    Prev
    Next
    INDEX
    Explanations

    mentions of anchovies or related terms 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
    edn
    -0.07
    auss
    -0.07
    ownt
    -0.07
     ais
    -0.07
    oins
    -0.06
    767
    -0.06
    osate
    -0.06
    .rnn
    -0.06
    лÑİб
    -0.06
    inherits
    -0.06
    POSITIVE LOGITS
    orage
    0.20
    ORAGE
    0.14
    uria
    0.09
    orman
    0.09
    argo
    0.09
    ored
    0.08
    ors
    0.08
    ovy
    0.08
    mi
    0.08
    ovies
    0.08
    Activations Density 0.004%

    No Known Activations