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. 8-LLAMASCOPE-RES-32K
    6. 22921
    Prev
    Next
    INDEX
    Explanations

    quantitative references related to frequency and consistency in activities or events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 8-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ollipop
    -0.15
    ample
    -0.15
    ulum
    -0.15
    abad
    -0.14
    gere
    -0.14
    лÑĭ
    -0.14
    yp
    -0.14
     Harbour
    -0.14
    etype
    -0.14
    aru
    -0.14
    POSITIVE LOGITS
     each
    0.25
    each
    0.21
     má»Ĺi
    0.20
     кажд
    0.19
     каждого
    0.18
     Each
    0.18
    æ¯ı
    0.18
     every
    0.18
     æ¯ı
    0.18
     każ
    0.18
    Activations Density 0.281%

    No Known Activations