© 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. 13-LLAMASCOPE-RES-32K
    11. 15621
    Prev
    Next
    INDEX
    Explanations

    capitalized nouns related to objects, concepts, and actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    éŀ
    -0.14
    OLUMN
    -0.14
    rlen
    -0.13
    à¹Ģà¸ģà¸Ńร
    -0.13
    antt
    -0.13
    actionDate
    -0.13
    illaume
    -0.12
    inerary
    -0.12
    podob
    -0.12
     \"
    -0.12
    POSITIVE LOGITS
    oka
    0.14
    osate
    0.14
    ãģĵãĤĵãģ«ãģ¡ãģ¯
    0.14
    dda
    0.13
    308
    0.13
    tees
    0.13
    yne
    0.13
     Certif
    0.13
    inis
    0.13
    yme
    0.13
    Activations Density 0.754%

    No Known Activations