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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 3-LLAMASCOPE-RES-32K
    6. 24169
    Prev
    Next
    INDEX
    Explanations

    terms related to risk reduction and management strategies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 3-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L3R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    .truth
    -0.17
     çĬ
    -0.16
    iets
    -0.16
    slu
    -0.16
    ATCH
    -0.15
    sst
    -0.15
    ÄĻż
    -0.15
    airo
    -0.15
    ãĤ¹ãĥ¬
    -0.14
    nothrow
    -0.14
    POSITIVE LOGITS
    ology
    0.14
    resse
    0.14
    ation
    0.14
    inerary
    0.14
     gia
    0.14
    ating
    0.13
    /pre
    0.13
     Bol
    0.13
    rob
    0.13
     circumstances
    0.13
    Activations Density 0.011%

    No Known Activations