© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 30-LLAMASCOPE-RES-32K
    6. 12267
    Prev
    Next
    INDEX
    Explanations

    references to events in the present or near future

    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
    -calendar
    -0.16
     Calendar
    -0.16
    ëį°ìĿ´íĬ¸
    -0.15
     calend
    -0.15
    eyh
    -0.14
    Uni
    -0.14
    éĹ
    -0.14
    ncia
    -0.14
    ç±į
    -0.14
    inerary
    -0.14
    POSITIVE LOGITS
     years
    0.35
     editions
    0.28
     edition
    0.26
    years
    0.23
    edition
    0.23
     weekends
    0.22
    -years
    0.22
    åĬĽçļĦ
    0.21
     weeks
    0.20
     summers
    0.20
    Activations Density 0.035%

    No Known Activations