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. 15-LLAMASCOPE-RES-32K
    6. 25084
    Prev
    Next
    INDEX
    Explanations

    phrases involving significant amounts of investment or funding

    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
    TURE
    -0.15
    plusplus
    -0.15
    _PRIORITY
    -0.14
    unce
    -0.14
    __;
    -0.14
    ould
    -0.14
    afd
    -0.14
    _cou
    -0.14
    421
    -0.14
    abar
    -0.14
    POSITIVE LOGITS
    atz
    0.14
     ëĦ¤ìĿ´íĬ¸
    0.13
     Hacker
    0.13
    ,
    0.13
    OBJ
    0.13
    å®Ĺ
    0.13
     voks
    0.13
    REA
    0.13
    /uploads
    0.13
    esso
    0.13
    Activations Density 0.288%

    No Known Activations