© 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. 11-LLAMASCOPE-RES-32K
    11. 20647
    Prev
    Next
    INDEX
    Explanations

    occurrences of the verbs "see" and "saw," along with phrases indicating observation or experience

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    imson
    -0.15
    woke
    -0.15
    822
    -0.14
     lesson
    -0.14
    ieres
    -0.13
    evin
    -0.13
    322
    -0.13
     Lesson
    -0.13
    lee
    -0.13
    isclosed
    -0.13
    POSITIVE LOGITS
    iqueta
    0.15
    ams
    0.15
    iard
    0.15
    iams
    0.15
    æŁľ
    0.15
    AMS
    0.15
     tá»Ń
    0.14
     perd
    0.14
    §
    0.13
     favor
    0.13
    Activations Density 0.071%

    No Known Activations