© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 15-LLAMASCOPE-RES-131K
    11. 90315
    Prev
    Next
    INDEX
    Explanations

    references to titles or names

    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
    reon
    -0.08
     Ùĥر
    -0.07
    TextColor
    -0.07
    ponge
    -0.07
    å¢ĥ
    -0.07
    elon
    -0.07
    versions
    -0.07
    ="{!!
    -0.07
    åĩ¡
    -0.07
    erif
    -0.07
    POSITIVE LOGITS
     called
    0.12
     name
    0.11
    åı«
    0.10
    called
    0.10
     named
    0.10
     titled
    0.09
    -called
    0.09
     names
    0.09
    称
    0.09
    åIJį
    0.08
    Activations Density 0.022%

    No Known Activations