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. 4-LLAMASCOPE-RES-32K
    6. 30940
    Prev
    Next
    INDEX
    Explanations

    verbs indicating possession or existence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ÑĢÑĥд
    -0.17
    ixel
    -0.17
    ãĥ³ãĤ¹
    -0.16
    741
    -0.16
    å¦ĥ
    -0.15
    uler
    -0.15
    apons
    -0.15
    ÑĢал
    -0.15
    oux
    -0.15
    otre
    -0.15
    POSITIVE LOGITS
     Maiden
    0.14
    quip
    0.14
    lili
    0.14
    BarButton
    0.14
    anken
    0.14
    urai
    0.13
    addon
    0.13
     priorities
    0.13
     passenger
    0.13
    udder
    0.13
    Activations Density 0.146%

    No Known Activations