© 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. 17284
    Prev
    Next
    INDEX
    Explanations

    references to temporal concepts like "past" and "present."

    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
    (Pointer
    -0.15
     Payne
    -0.15
    phin
    -0.14
    ocker
    -0.13
    paque
    -0.13
     Playoff
    -0.13
    etine
    -0.13
    Playable
    -0.13
    æľĽ
    -0.13
    using
    -0.13
    POSITIVE LOGITS
     present
    1.03
    present
    0.99
     Present
    0.94
    -present
    0.92
    Present
    0.90
     presents
    0.88
    _present
    0.82
     présent
    0.82
     presented
    0.80
     presentation
    0.80
    Activations Density 0.208%

    No Known Activations