© 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. 31-LLAMASCOPE-RES-32K
    11. 17904
    Prev
    Next
    INDEX
    Explanations

    symbols and special characters that may indicate technical or digital content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    .ide
    -0.15
    !*
    -0.14
     coloured
    -0.14
     humour
    -0.14
    ÑĪин
    -0.14
    colour
    -0.13
    ceed
    -0.13
     programmes
    -0.13
     favourites
    -0.13
     programme
    -0.13
    POSITIVE LOGITS
     âĢ¦
    0.27
     TMZ
    0.24
     ppl
    0.23
     cuz
    0.21
     ...
    0.21
     cops
    0.20
     biz
    0.20
     gotta
    0.19
     $$$
    0.19
     gonna
    0.19
    Activations Density 0.004%

    No Known Activations