© 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. 31-LLAMASCOPE-RES-32K
    11. 31424
    Prev
    Next
    INDEX
    Explanations

    references to hope and optimism in challenging situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    aghetti
    -0.14
     knull
    -0.14
    UnderTest
    -0.14
    ikut
    -0.13
    (priority
    -0.13
    jezd
    -0.12
    ³»
    -0.12
     ÅĻ
    -0.12
    urtles
    -0.12
    .skin
    -0.12
    POSITIVE LOGITS
     optimism
    0.55
     optimistic
    0.52
     hopeful
    0.50
     hope
    0.47
    optim
    0.46
     Optim
    0.46
     optim
    0.45
    hope
    0.40
     опÑĤим
    0.40
     Hope
    0.40
    Activations Density 0.324%

    No Known Activations