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. 17-LLAMASCOPE-RES-32K
    6. 15955
    Prev
    Next
    INDEX
    Explanations

    descriptors of community and identity, particularly in the context of diverse experiences and backgrounds

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ocker
    -0.16
    ionic
    -0.16
    akis
    -0.14
     Jennings
    -0.14
    çak
    -0.13
    stands
    -0.13
     Bez
    -0.13
    )prepare
    -0.13
    ENA
    -0.13
     åīį
    -0.12
    POSITIVE LOGITS
     stuff
    0.19
     ones
    0.17
     things
    0.15
    ness
    0.15
     thing
    0.14
    ofday
    0.14
    wor
    0.14
    -пÑĢав
    0.14
     ways
    0.14
    282
    0.14
    Activations Density 0.446%

    No Known Activations