© 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. 30-LLAMASCOPE-RES-32K
    6. 11589
    Prev
    Next
    INDEX
    Explanations

    references to divinity and spirituality, particularly in relation to grace and redemption

    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
     chuck
    -0.21
     penetr
    -0.20
     erupt
    -0.18
     eject
    -0.18
     eaten
    -0.18
     deflect
    -0.18
     patter
    -0.18
     bitten
    -0.18
     blink
    -0.18
     flown
    -0.18
    POSITIVE LOGITS
     did
    0.26
     wound
    0.26
     didn
    0.24
     chose
    0.23
     saw
    0.22
     bore
    0.21
     got
    0.21
     gave
    0.21
     took
    0.21
     interact
    0.21
    Activations Density 2.811%

    No Known Activations