© 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. 30-LLAMASCOPE-RES-32K
    11. 10891
    Prev
    Next
    INDEX
    Explanations

    references to scientific articles and publications, specifically in the context of food science and technology

    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
    åħ¸
    -0.15
     /
    -0.14
    readcr
    -0.13
     Pu
    -0.13
     th
    -0.13
    reck
    -0.13
    inch
    -0.13
    Moder
    -0.12
     Mag
    -0.12
     III
    -0.12
    POSITIVE LOGITS
    %
    0.23
    .%
    0.21
    %C
    0.18
    %D
    0.17
    .tb
    0.17
    %E
    0.16
     pii
    0.16
    %f
    0.16
    ?url
    0.16
    200
    0.15
    Activations Density 0.051%

    No Known Activations