Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 29-LLAMASCOPE-RES-32K
    6. 16398
    Prev
    Next
    INDEX
    Explanations

    mentions of popular streaming and music services

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.29.hook_resid_post
    Hook Layer
    29
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Wikip
    -0.15
    ÙİÙĬ
    -0.15
     Tweet
    -0.14
    گر
    -0.14
     Tweets
    -0.14
    λÎŃ
    -0.14
    .googlecode
    -0.14
     Hlav
    -0.14
    lush
    -0.14
    Fraction
    -0.14
    POSITIVE LOGITS
    .com
    0.49
    .COM
    0.32
    .co
    0.28
    .org
    0.27
    .ca
    0.26
    .Com
    0.25
    .de
    0.24
    usercontent
    0.23
    .net
    0.22
    .fr
    0.22
    Activations Density 0.138%

    No Known Activations