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. 11487
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols or terms related to parameters and variables in equations

    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
     Lexington
    -0.06
    terraform
    -0.06
     demeanor
    -0.06
     amazon
    -0.06
    å½
    -0.05
    IRECTION
    -0.05
     Chester
    -0.05
     Bombay
    -0.05
     Trafford
    -0.05
    .amazon
    -0.05
    POSITIVE LOGITS
     MOVE
    0.15
    MOVE
    0.12
     European
    0.11
     EU
    0.11
     Move
    0.11
     Europe
    0.11
     EURO
    0.10
     MOV
    0.10
    European
    0.10
     Europ
    0.10
    Activations Density 0.004%

    No Known Activations