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. 23-LLAMASCOPE-RES-32K
    6. 30556
    Prev
    Next
    INDEX
    Explanations

    numerical data, specifically referencing statistical values or metrics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ÑĪка
    -0.16
    roe
    -0.16
    ù
    -0.15
    hatt
    -0.15
    robe
    -0.14
    tridges
    -0.14
    luet
    -0.13
    éra
    -0.13
    978
    -0.13
    ajo
    -0.13
    POSITIVE LOGITS
     Qed
    0.15
    oundation
    0.14
    cad
    0.14
    keley
    0.14
    ehler
    0.14
    lik
    0.14
    зв
    0.14
    ĵĺ
    0.13
    usch
    0.13
    ENCES
    0.13
    Activations Density 0.051%

    No Known Activations