© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 30-LLAMASCOPE-RES-32K
    11. 5613
    Prev
    Next
    INDEX
    Explanations

    elements and functions related to object properties and methods in programming

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    holm
    -0.17
    vrier
    -0.16
    bral
    -0.16
    Outcome
    -0.16
    =image
    -0.15
     Operation
    -0.15
    ,image
    -0.15
     Opera
    -0.15
     Orders
    -0.15
     hol
    -0.15
    POSITIVE LOGITS
     obj
    0.90
    (obj
    0.87
    =obj
    0.77
    obj
    0.75
    [obj
    0.73
    	obj
    0.71
    ,obj
    0.69
    .obj
    0.68
    )obj
    0.65
    _obj
    0.55
    Activations Density 0.023%

    No Known Activations