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. 25-LLAMASCOPE-RES-32K
    6. 17953
    Prev
    Next
    INDEX
    Explanations

    numerical data and statistics related to organizations or memberships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    lesen
    -0.16
    ochen
    -0.15
    .cms
    -0.15
     Ãĩev
    -0.15
    getService
    -0.14
    acons
    -0.14
    aklı
    -0.14
    tuk
    -0.14
    halb
    -0.13
     ÑĢеж
    -0.13
    POSITIVE LOGITS
     club
    0.27
     playing
    0.23
    playing
    0.20
     clubs
    0.20
     play
    0.19
     played
    0.19
     amateur
    0.19
     plays
    0.19
     amateurs
    0.18
     клÑĥб
    0.18
    Activations Density 0.020%

    No Known Activations