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. 27-LLAMASCOPE-RES-32K
    6. 12065
    Prev
    Next
    INDEX
    Explanations

    references to the well-being and future of individuals and families within a community context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.27.hook_resid_post
    Hook Layer
    27
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    że
    -0.14
    ycled
    -0.14
    edido
    -0.14
    боÑĢ
    -0.13
     brutality
    -0.13
    νή
    -0.13
    abor
    -0.13
    trusted
    -0.13
    豪
    -0.13
     Complexity
    -0.12
    POSITIVE LOGITS
     welfare
    0.52
     wellbeing
    0.46
     safety
    0.40
     survival
    0.39
     health
    0.38
     Welfare
    0.38
     well
    0.36
     future
    0.34
    elfare
    0.34
     fate
    0.34
    Activations Density 0.318%

    No Known Activations