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. 30-LLAMASCOPE-RES-32K
    6. 18812
    Prev
    Next
    INDEX
    Explanations

    emotional expressions of gratitude and affection

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    incy
    -0.16
    hydrate
    -0.16
    á»§y
    -0.15
    Ïį
    -0.15
    itur
    -0.14
    duto
    -0.14
    _AA
    -0.14
    alcon
    -0.13
    Hashtable
    -0.13
     Hull
    -0.13
    POSITIVE LOGITS
     heart
    1.09
     Heart
    0.91
    heart
    0.89
    -heart
    0.85
    Heart
    0.84
     hearts
    0.83
    å¿ĥ
    0.71
     ÑģеÑĢд
    0.68
     Hearts
    0.67
     å¿ĥ
    0.62
    Activations Density 0.173%

    No Known Activations