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. 26-LLAMASCOPE-RES-32K
    6. 22222
    Prev
    Next
    INDEX
    Explanations

    geographical and location-related terms within the context of urban infrastructure and water management

    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
     soul
    -0.16
    ceiver
    -0.15
    clipse
    -0.15
    idth
    -0.15
     Worm
    -0.15
    .BorderFactory
    -0.15
    æĹıèĩªæ²»
    -0.14
    å±±å¸Ĥ
    -0.14
     bitmask
    -0.14
    عÙĦÙĪÙħات
    -0.14
    POSITIVE LOGITS
    pur
    0.29
     pur
    0.22
     Gram
    0.21
    gram
    0.20
     gram
    0.20
     Colony
    0.19
    abad
    0.19
    PUR
    0.19
     Pur
    0.18
    apur
    0.18
    Activations Density 0.148%

    No Known Activations