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. 9-LLAMASCOPE-RES-32K
    6. 21507
    Prev
    Next
    INDEX
    Explanations

    mentions of copyright information and licensing terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     downs
    -0.18
     Downs
    -0.16
    ighton
    -0.15
    ToWorld
    -0.14
    up
    -0.14
     Zub
    -0.14
    aj
    -0.14
     pig
    -0.14
    94
    -0.14
     Down
    -0.14
    POSITIVE LOGITS
     putas
    0.15
    yleft
    0.14
    ombine
    0.13
    _MEMBERS
    0.13
    brtc
    0.13
    .dispatch
    0.13
    .family
    0.13
    uzu
    0.13
    umeric
    0.13
     Mash
    0.13
    Activations Density 0.041%

    No Known Activations