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. 13-LLAMASCOPE-RES-32K
    6. 15366
    Prev
    Next
    INDEX
    Explanations

    symbols and punctuation marks used for emphasis or separation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ses
    -0.28
    /her
    -0.17
    ssc
    -0.16
    ese
    -0.16
    ’t
    -0.15
    nt
    -0.15
    aneous
    -0.14
    athan
    -0.14
    sss
    -0.14
    sed
    -0.14
    POSITIVE LOGITS
    amp
    0.49
    nbsp
    0.39
    raquo
    0.32
    ÑĶм
    0.30
    quot
    0.28
    AMP
    0.28
    apos
    0.26
    emsp
    0.24
    ï¸ı
    0.23
     amp
    0.19
    Activations Density 0.055%

    No Known Activations