© 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. 15-LLAMASCOPE-RES-32K
    11. 9270
    Prev
    Next
    INDEX
    Explanations

    occurrences of frequent words and phrases in a specific context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    arga
    -0.17
     Cobb
    -0.15
     Nationals
    -0.15
    ãģĹãģı
    -0.15
    à¸ķร
    -0.14
    .DisplayMember
    -0.14
    ultan
    -0.14
    ehler
    -0.13
    lauf
    -0.13
    ãĤ«ãĥ¼
    -0.13
    POSITIVE LOGITS
    vak
    0.17
     haci
    0.15
    169
    0.15
    .shtml
    0.14
    ÑĨин
    0.14
     Hin
    0.13
    357
    0.13
    arry
    0.13
    elize
    0.13
    ìĨį
    0.13
    Activations Density 0.001%

    No Known Activations