© 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. 29-LLAMASCOPE-RES-32K
    11. 13027
    Prev
    Next
    INDEX
    Explanations

    mentions of ways to obtain services or items

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.29.hook_resid_post
    Hook Layer
    29
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    duÄŁ
    -0.14
    .DateTimePicker
    -0.14
    egend
    -0.14
    ç§ģãģ®
    -0.14
    ItemAt
    -0.14
    kinci
    -0.14
    edback
    -0.13
    óż
    -0.13
    _TAC
    -0.13
    arih
    -0.13
    POSITIVE LOGITS
     themselves
    1.47
     itself
    1.41
     himself
    1.36
     herself
    1.35
     yourself
    1.15
     Himself
    1.14
     ourselves
    1.12
     oneself
    1.07
     yourselves
    1.05
     Yourself
    1.02
    Activations Density 1.770%

    No Known Activations