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. 21-LLAMASCOPE-RES-32K
    6. 8422
    Prev
    Next
    INDEX
    Explanations

    references to companies and their relationships or developments in the tech industry

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 21-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L21R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    istra
    -0.16
    ERENCE
    -0.14
    Ñĩин
    -0.14
    ารย
    -0.14
    .Compile
    -0.13
    ugu
    -0.13
    zÃŃ
    -0.13
    ãĥ¼ãĥĨ
    -0.13
    é¼
    -0.13
    alla
    -0.13
    POSITIVE LOGITS
     realization
    0.77
     realize
    0.71
     realizes
    0.69
     realized
    0.67
     realizing
    0.64
     realise
    0.60
     realised
    0.56
     recognition
    0.46
     realiz
    0.45
     awareness
    0.44
    Activations Density 0.603%

    No Known Activations