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. 16-LLAMASCOPE-RES-32K
    6. 21719
    Prev
    Next
    INDEX
    Explanations

    dialogue and expressions of speech

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ogh
    -0.15
    RuleContext
    -0.15
    aint
    -0.14
     sche
    -0.14
     eldre
    -0.14
     Sinai
    -0.14
     åĽ
    -0.13
    shm
    -0.13
    _signed
    -0.13
    _cpp
    -0.13
    POSITIVE LOGITS
    itel
    0.14
     aller
    0.14
    umer
    0.14
    nic
    0.13
    иÑģÑĤ
    0.13
    ux
    0.13
     blinded
    0.13
     bilin
    0.13
    EQ
    0.13
    astery
    0.13
    Activations Density 0.003%

    No Known Activations