© 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. 93603
    Prev
    Next
    INDEX
    Explanations

    themes of communication and representation for those who cannot express themselves

    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
    ader
    -0.07
     tô
    -0.06
    DataReader
    -0.06
    SSF
    -0.06
    adero
    -0.06
    hest
    -0.06
     Nic
    -0.06
    ondo
    -0.06
    StateException
    -0.06
     Blick
    -0.06
    POSITIVE LOGITS
     voice
    0.14
     voices
    0.11
     representation
    0.10
     vo
    0.10
    voice
    0.10
     speak
    0.10
     speaking
    0.10
     Voice
    0.10
     Representation
    0.10
     silenced
    0.09
    Activations Density 0.035%

    No Known Activations