© 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. 17-LLAMASCOPE-RES-32K
    11. 21704
    Prev
    Next
    INDEX
    Explanations

    code snippets related to method invocation and reflection in programming

    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
    odel
    -0.17
    irable
    -0.15
    _ED
    -0.14
    flo
    -0.14
    antine
    -0.14
     getline
    -0.14
    ENOMEM
    -0.14
    stvo
    -0.13
    Flo
    -0.13
     builder
    -0.13
    POSITIVE LOGITS
     Reflection
    0.20
     reflections
    0.20
    reflect
    0.18
    .Reflection
    0.18
    reflection
    0.18
    Reflection
    0.18
     reflect
    0.18
    TypeInfo
    0.18
     Reflect
    0.17
     reflection
    0.17
    Activations Density 0.501%

    No Known Activations