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. 44333
    Prev
    Next
    INDEX
    Explanations

    special characters or non-standard symbols

    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
    Âł
    -0.08
     â̦
    -0.06
     –
    -0.06
     [â̦]
    -0.06
    â̦
    -0.05
     âĢŀ
    -0.05
    â̦I
    -0.05
     [â̦]↵
    -0.05
     precip
    -0.05
     BD
    -0.05
    POSITIVE LOGITS
     poems
    0.12
     poem
    0.11
    è¯Ĺ
    0.10
     motivational
    0.10
     poets
    0.09
     poet
    0.09
     poetry
    0.09
    è©©
    0.09
    anonymous
    0.08
     Poetry
    0.08
    Activations Density 0.003%

    No Known Activations