© 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. 31-LLAMASCOPE-RES-32K
    11. 30920
    Prev
    Next
    INDEX
    Explanations

    variations of the name "Nagle" and its related forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    даеÑĤÑģÑı
    -0.11
    лива
    -0.10
    ียà¸Ķ
    -0.10
    λÏī
    -0.09
    ãĥ¼ãĥĨ
    -0.09
    OMUX
    -0.09
    krv
    -0.09
     springfox
    -0.09
    ;:;:
    -0.08
    λÏİ
    -0.08
    POSITIVE LOGITS
    ÂłN
    0.69
    -N
    0.67
    /N
    0.61
    ,N
    0.60
    _N
    0.58
    [N
    0.58
     NR
    0.58
    (N
    0.57
    .N
    0.57
     NM
    0.57
    Activations Density 2.929%

    No Known Activations