Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 9-LLAMASCOPE-RES-131K
    6. 96005
    Prev
    Next
    INDEX
    Explanations

    informal expressions and conversational phrases

    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
    اÙĪÙĬØ©
    -0.07
    -translate
    -0.07
    ष
    -0.07
    gom
    -0.07
    .ease
    -0.07
    ÑĤап
    -0.06
    ÑĪÑĮ
    -0.06
    turnstile
    -0.06
    chaft
    -0.06
    pling
    -0.06
    POSITIVE LOGITS
    æļ
    0.07
     Dixon
    0.07
     drop
    0.06
    abus
    0.06
    mina
    0.06
     distortion
    0.06
    enthal
    0.06
     Sung
    0.06
     confusion
    0.06
    MG
    0.06
    Activations Density 0.014%

    No Known Activations