© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 16-LLAMASCOPE-RES-32K
    11. 6601
    Prev
    Next
    INDEX
    Explanations

    elements related to strategic decision-making and planning in various contexts

    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
    ĺIJ
    -0.14
    deme
    -0.14
    ennent
    -0.14
    bulan
    -0.14
    avan
    -0.14
    eyse
    -0.13
     GlobalKey
    -0.13
    usting
    -0.13
    erable
    -0.13
     Bounds
    -0.13
    POSITIVE LOGITS
     accordingly
    0.33
     based
    0.22
     Accordingly
    0.22
    appropriate
    0.20
     appropriate
    0.20
     correspond
    0.18
     next
    0.17
     Based
    0.17
     actions
    0.17
     decisions
    0.17
    Activations Density 0.157%

    No Known Activations