© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 8-LLAMASCOPE-RES-32K
    6. 23059
    Prev
    Next
    INDEX
    Explanations

    details related to geographical locations or addresses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 8-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    breadcrumb
    -0.15
     (?)
    -0.14
    gy
    -0.14
    aign
    -0.14
     miá»ħn
    -0.14
    ium
    -0.14
     faz
    -0.14
    .tel
    -0.14
    istik
    -0.13
    rega
    -0.13
    POSITIVE LOGITS
    ÎŃλ
    0.14
    ê·¸ëŁ¬
    0.14
    ãģ¯ãģªãģĦ
    0.14
    ptal
    0.14
     Cle
    0.14
     Všech
    0.13
     наÑĢÑĥж
    0.13
    [level
    0.13
    xea
    0.13
    asan
    0.13
    Activations Density 4.601%

    No Known Activations