© 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. 4-LLAMASCOPE-RES-32K
    6. 3493
    Prev
    Next
    INDEX
    Explanations

    references to the name "Anderson" and related variations

    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
    алом
    -0.16
    stab
    -0.16
    owing
    -0.15
     nÃło
    -0.15
    ijIJ
    -0.15
    âĢĮاÙĦ
    -0.14
    ehr
    -0.14
    idl
    -0.14
    neau
    -0.14
    akah
    -0.14
    POSITIVE LOGITS
    /OR
    0.15
    istant
    0.15
    jan
    0.15
    over
    0.15
    ocking
    0.14
    zej
    0.14
    ä¸Ķ
    0.14
    eries
    0.14
    hell
    0.14
    /or
    0.14
    Activations Density 0.020%

    No Known Activations