© 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. 28-LLAMASCOPE-RES-32K
    11. 23488
    Prev
    Next
    INDEX
    Explanations

    instances of quantifiable data and statistics related to people and activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    á»ĵ
    -0.15
    PrivateKey
    -0.15
    .pnl
    -0.14
    ÑħÑĢан
    -0.14
     Pound
    -0.14
     Patterson
    -0.13
    /pi
    -0.13
    ÑĮко
    -0.13
    ToWorld
    -0.13
    uyu
    -0.13
    POSITIVE LOGITS
     pass
    1.20
     passes
    1.12
     passing
    1.09
    -pass
    1.08
     passed
    1.06
    pass
    1.06
     Pass
    1.05
    Pass
    0.97
    _pass
    0.95
     Passing
    0.94
    Activations Density 0.248%

    No Known Activations