Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 22-LLAMASCOPE-RES-32K
    6. 4342
    Prev
    Next
    INDEX
    Explanations

    topics related to astronomy and astrophysics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    .Prot
    -0.17
    ATAR
    -0.15
    ëĤĺ무
    -0.14
     McKay
    -0.14
    foot
    -0.14
    İ
    -0.14
    347
    -0.13
    олоÑĤ
    -0.13
    osc
    -0.13
    ovable
    -0.13
    POSITIVE LOGITS
    è½®
    0.19
     galaxies
    0.18
    spir
    0.18
     recess
    0.18
     гал
    0.17
     ÑģпиÑĢ
    0.17
    emiz
    0.17
     spiral
    0.17
     galaxy
    0.17
    gal
    0.16
    Activations Density 0.009%

    No Known Activations