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. 3-LLAMASCOPE-RES-32K
    6. 23681
    Prev
    Next
    INDEX
    Explanations

    numerical statistics related to game performance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 3-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L3R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     cones
    -0.15
     Liver
    -0.15
    ÙħÙĤ
    -0.14
    å°ĸ
    -0.14
    zhou
    -0.14
     extras
    -0.13
     Miy
    -0.13
    uur
    -0.13
    STD
    -0.13
    ider
    -0.13
    POSITIVE LOGITS
    eus
    0.17
    okens
    0.17
    okus
    0.16
    zcze
    0.15
    itmap
    0.15
    oux
    0.15
    686
    0.15
    lint
    0.14
    ppelin
    0.14
    estroy
    0.14
    Activations Density 0.202%

    No Known Activations