© 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. 25-LLAMASCOPE-RES-32K
    11. 17803
    Prev
    Next
    INDEX
    Explanations

    references to online applications and event registrations

    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
    isify
    -0.17
    /goto
    -0.17
    -Isl
    -0.16
    ảy
    -0.14
    opher
    -0.14
    práv
    -0.14
    ा:
    -0.14
     YYSTYPE
    -0.14
    <HashMap
    -0.14
    mbH
    -0.14
    POSITIVE LOGITS
    .html
    0.38
    .htm
    0.30
    /)
    0.24
    /↵
    0.23
    /,
    0.23
    .aspx
    0.22
    /↵↵
    0.21
     html
    0.20
    /index
    0.20
    /)↵
    0.20
    Activations Density 0.095%

    No Known Activations