© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 18-LLAMASCOPE-RES-32K
    6. 2805
    Prev
    Next
    INDEX
    Explanations

    instances of the word "Throughout" signifying the continuation or consistency of an idea or theme in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    .scenes
    -0.17
     Dunk
    -0.14
    sse
    -0.14
    heimer
    -0.14
    urus
    -0.14
    ãĤĪãģĨ
    -0.13
    ãĤ©
    -0.13
     halt
    -0.13
    erral
    -0.13
    ion
    -0.13
    POSITIVE LOGITS
    tej
    0.18
    stant
    0.17
    SetBranch
    0.17
    ason
    0.15
    IGHLIGHT
    0.15
    šak
    0.15
    quito
    0.15
    ihn
    0.15
    rippling
    0.15
    teen
    0.14
    Activations Density 0.017%

    No Known Activations