© 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. 82724
    Prev
    Next
    INDEX
    Explanations

    emotive and descriptive qualities related to voice and 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
    apiro
    -0.07
    oref
    -0.07
    год
    -0.06
     promotion
    -0.06
    ourg
    -0.06
    sess
    -0.06
     Streams
    -0.06
    znik
    -0.06
    dfa
    -0.06
    aksi
    -0.06
    POSITIVE LOGITS
     voice
    0.12
     голоÑģ
    0.09
     Voice
    0.09
    voice
    0.09
     voices
    0.09
     nasal
    0.08
     tone
    0.08
     vo
    0.08
    Voice
    0.07
     voz
    0.07
    Activations Density 0.037%

    No Known Activations