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. 5598
    Prev
    Next
    INDEX
    Explanations

    references to literary and cultural criticism

    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
    çĥ
    -0.07
    bens
    -0.07
    /forum
    -0.07
    éro
    -0.07
    опаÑģ
    -0.07
    agedList
    -0.07
    &uuml
    -0.06
    #__
    -0.06
    ano
    -0.06
    iÄį
    -0.06
    POSITIVE LOGITS
    49
    0.07
    37
    0.07
    19
    0.07
    18
    0.06
    8
    0.06
    68
    0.06
    26
    0.06
     needs
    0.06
    CDATA
    0.06
    28
    0.06
    Activations Density 0.019%

    No Known Activations