© 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. 5-LLAMASCOPE-RES-32K
    11. 17880
    Prev
    Next
    INDEX
    Explanations

    expressions and variations of intention and intent 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 @ 5-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    istrovstvÃŃ
    -0.15
    INCREMENT
    -0.14
    essler
    -0.14
    "description
    -0.14
    ÑĤоÑĢ
    -0.13
    rectangle
    -0.13
    rist
    -0.13
    ÑĨо
    -0.13
    /movie
    -0.13
    adera
    -0.13
    POSITIVE LOGITS
     intent
    0.18
    .CopyTo
    0.15
    intent
    0.15
    full
    0.15
    ofile
    0.15
    ادا
    0.15
    GetProperty
    0.15
    FUL
    0.15
    ilst
    0.14
    bpp
    0.14
    Activations Density 0.024%

    No Known Activations