© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 78156
    Prev
    Next
    INDEX
    Explanations

    phrases indicating speech or communication

    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
    wers
    -0.08
    LOPT
    -0.07
    ushman
    -0.07
    ãĥ³ãĥĦ
    -0.07
    SCRI
    -0.07
    imeline
    -0.07
    ollipop
    -0.07
    nero
    -0.07
    enz
    -0.07
    asics
    -0.07
    POSITIVE LOGITS
     speaking
    0.38
     Speaking
    0.35
    Speaking
    0.33
    -speaking
    0.27
     speak
    0.26
    spe
    0.26
     speaks
    0.23
     spoke
    0.21
     spoken
    0.20
     Speak
    0.20
    Activations Density 0.126%

    No Known Activations