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. 19-LLAMASCOPE-RES-32K
    6. 25888
    Prev
    Next
    INDEX
    Explanations

    street addresses and location details

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    bris
    -0.15
    çĭ¼
    -0.14
    obra
    -0.14
    icari
    -0.14
     Ocak
    -0.14
    ollipop
    -0.14
    實
    -0.13
     blow
    -0.13
    ково
    -0.13
     поз
    -0.13
    POSITIVE LOGITS
     Suite
    0.35
    Suite
    0.34
     suite
    0.30
    suite
    0.29
    -suite
    0.24
     Ste
    0.23
     UNIT
    0.22
     Apt
    0.21
     STE
    0.21
     Unit
    0.21
    Activations Density 0.169%

    No Known Activations