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. 44377
    Prev
    Next
    INDEX
    Explanations

    references to specific attributes or elements within a narrative 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
    orny
    -0.06
     mdi
    -0.06
    ritten
    -0.06
    ãĥ¼ãĥĢ
    -0.06
    igger
    -0.06
     Arrest
    -0.06
     maduras
    -0.06
    kili
    -0.06
     Contemporary
    -0.06
     -------------------------------------------------------------------------↵
    -0.06
    POSITIVE LOGITS
     evil
    0.15
     ancient
    0.12
     supernatural
    0.12
     warriors
    0.11
     undead
    0.11
     demonic
    0.11
     warrior
    0.11
     magical
    0.11
     sinister
    0.11
     creatures
    0.10
    Activations Density 0.017%

    No Known Activations