© 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. 2287
    Prev
    Next
    INDEX
    Explanations

    phrases indicating anticipation or looking forward to future events

    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
     preferring
    -0.14
     opting
    -0.14
     opts
    -0.14
     prefers
    -0.14
     willing
    -0.13
     bothered
    -0.13
    bens
    -0.13
     beden
    -0.13
    olare
    -0.13
     demanded
    -0.13
    POSITIVE LOGITS
     hearing
    0.27
     many
    0.24
     continued
    0.23
     future
    0.22
     seeing
    0.21
     opportunities
    0.21
     continue
    0.20
     welcoming
    0.20
     Hearing
    0.20
     hopefully
    0.20
    Activations Density 0.056%

    No Known Activations