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. 27-LLAMASCOPE-RES-32K
    6. 19183
    Prev
    Next
    INDEX
    Explanations

    instances of hyperlinks and their connections within the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.27.hook_resid_post
    Hook Layer
    27
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    473
    -0.17
    duc
    -0.17
    nier
    -0.15
    vÃŃ
    -0.15
    een
    -0.15
    ughter
    -0.15
    442
    -0.15
    ccione
    -0.15
    Iron
    -0.15
    ISTIC
    -0.15
    POSITIVE LOGITS
    ages
    0.42
    AGES
    0.28
    age
    0.27
    edin
    0.25
    aged
    0.21
    sys
    0.21
    /button
    0.21
    din
    0.21
    vertise
    0.20
    spam
    0.20
    Activations Density 0.038%

    No Known Activations