© 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. 22-LLAMASCOPE-RES-32K
    6. 11112
    Prev
    Next
    INDEX
    Explanations

    concepts related to ecosystem management and population modeling in fisheries

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     pip
    -0.16
    ë§IJ
    -0.16
     Pip
    -0.15
    æ¤į
    -0.15
    wich
    -0.15
    elier
    -0.15
     خاک
    -0.15
     pipeline
    -0.14
    /helpers
    -0.14
     bottle
    -0.14
    POSITIVE LOGITS
     fisheries
    0.28
     fishing
    0.28
     catches
    0.26
     Fishing
    0.25
    quota
    0.23
     fishermen
    0.22
     fish
    0.22
    æ¼
    0.22
     harvest
    0.21
     Fisheries
    0.21
    Activations Density 0.108%

    No Known Activations