© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 31-LLAMASCOPE-RES-32K
    11. 9679
    Prev
    Next
    INDEX
    Explanations

    financial figures related to proposed investments or projects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    uxtap
    -0.15
    giene
    -0.13
    ptime
    -0.13
     ÑģоблÑİд
    -0.12
    IGHLIGHT
    -0.12
    овиÑĩ
    -0.12
    Ñģол
    -0.12
    à¸Ľà¸£à¸°à¸Īำ
    -0.11
    udoku
    -0.11
    overrides
    -0.11
    POSITIVE LOGITS
     proposal
    0.50
     proposals
    0.47
     plans
    0.46
     idea
    0.42
    proposal
    0.39
     ideas
    0.38
     proposed
    0.38
     plan
    0.37
     project
    0.36
     concept
    0.36
    Activations Density 1.594%

    No Known Activations