© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 30-LLAMASCOPE-RES-32K
    11. 17589
    Prev
    Next
    INDEX
    Explanations

    names and mentions of influential individuals or figures in various contexts

    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
    hash
    -0.15
    hang
    -0.15
    hint
    -0.15
    handle
    -0.13
    hack
    -0.13
    ilogy
    -0.12
    handles
    -0.12
    ìĨ
    -0.12
    hide
    -0.12
    hello
    -0.12
    POSITIVE LOGITS
    -H
    0.70
    ÂłH
    0.70
    (H
    0.67
    _H
    0.66
    	H
    0.63
     HC
    0.60
    ,H
    0.60
     HH
    0.59
     HB
    0.58
     HL
    0.57
    Activations Density 1.018%

    No Known Activations