© 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. 4-LLAMASCOPE-RES-32K
    11. 24941
    Prev
    Next
    INDEX
    Explanations

    discussions related to word count and the brevity and effectiveness of written content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ledon
    -0.15
     spe
    -0.15
    hait
    -0.14
    alley
    -0.14
    ade
    -0.14
     bonds
    -0.14
     Mills
    -0.14
    åĬ
    -0.13
     Basin
    -0.13
     bond
    -0.13
    POSITIVE LOGITS
    addle
    0.16
    боÑĤ
    0.15
    quare
    0.15
    stoff
    0.15
    éĺ
    0.15
    ary
    0.14
    aries
    0.14
    uchos
    0.14
    ÙIJب
    0.14
     stamped
    0.14
    Activations Density 0.288%

    No Known Activations