© 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. 9-LLAMASCOPE-RES-32K
    11. 26873
    Prev
    Next
    INDEX
    Explanations

    types and structures related to data representation in programming, specifically dictionaries and sets

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ancellor
    -0.14
    íĦ
    -0.14
    .onView
    -0.14
    csi
    -0.14
    stead
    -0.13
    reur
    -0.13
    coni
    -0.13
    ease
    -0.13
    quine
    -0.13
     hairs
    -0.13
    POSITIVE LOGITS
    illes
    0.15
     McG
    0.15
    uchen
    0.15
     \/
    0.14
    \.
    0.13
    assa
    0.13
    è§
    0.13
    olta
    0.13
     погод
    0.13
    alex
    0.13
    Activations Density 0.020%

    No Known Activations