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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 20-LLAMASCOPE-RES-32K
    6. 23795
    Prev
    Next
    INDEX
    Explanations

    mentions of content ownership and copyright protections

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ader
    -0.17
    off
    -0.15
     McCorm
    -0.15
    ple
    -0.15
    _ED
    -0.15
    ose
    -0.14
    -ton
    -0.14
    æģµ
    -0.14
     bri
    -0.14
    786
    -0.14
    POSITIVE LOGITS
     rights
    0.40
     Rights
    0.38
     RIGHTS
    0.32
     пÑĢава
    0.29
    Rights
    0.27
    -rights
    0.27
    _rights
    0.24
    rights
    0.24
     ØŃÙĤÙĪÙĤ
    0.19
    æĿĥ
    0.18
    Activations Density 0.008%

    No Known Activations