© 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. 26-LLAMASCOPE-RES-32K
    6. 5478
    Prev
    Next
    INDEX
    Explanations

    components related to algorithms for data retrieval and file sharing in distributed systems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 26-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L26R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.26.hook_resid_post
    Hook Layer
    26
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     autopsy
    -0.15
    /Foundation
    -0.14
    marshal
    -0.14
    عÙĦÙĪÙħ
    -0.14
    gard
    -0.14
    mez
    -0.13
    æij©
    -0.13
    ValuePair
    -0.13
    zia
    -0.13
     æ¥Ń
    -0.13
    POSITIVE LOGITS
     algorithm
    0.37
     algorithms
    0.34
     algo
    0.31
     scheme
    0.31
    -based
    0.30
     approach
    0.27
    ç®Ĺ
    0.27
     technique
    0.26
    algorithm
    0.26
     alg
    0.26
    Activations Density 0.175%

    No Known Activations