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. 18-LLAMASCOPE-RES-32K
    6. 28187
    Prev
    Next
    INDEX
    Explanations

    references to signs or indicators, particularly in the context of various topics or subjects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    stroy
    -0.16
    覧
    -0.15
    poons
    -0.15
    iggins
    -0.15
    ximity
    -0.15
    oucher
    -0.15
    ãĤ¤ãĤº
    -0.14
    òi
    -0.14
    ync
    -0.14
    alloca
    -0.14
    POSITIVE LOGITS
    ificantly
    0.31
    ificance
    0.27
    ificant
    0.25
    atures
    0.25
    atories
    0.24
    post
    0.23
    posts
    0.21
    alled
    0.21
    posted
    0.20
    posting
    0.19
    Activations Density 0.023%

    No Known Activations