© 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. 22-LLAMASCOPE-RES-32K
    11. 4888
    Prev
    Next
    INDEX
    Explanations

    concepts related to long-term goals and planning for future outcomes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    week
    -0.26
     week
    -0.23
     Weeks
    -0.22
    weeks
    -0.22
    Week
    -0.21
    -week
    -0.21
     Week
    -0.20
     weeks
    -0.19
    weekday
    -0.19
     fortn
    -0.19
    POSITIVE LOGITS
     decade
    0.58
     years
    0.57
     decades
    0.55
     Years
    0.52
    Years
    0.50
    years
    0.47
     YEARS
    0.44
     años
    0.39
     yrs
    0.39
    ä¸īå¹´
    0.39
    Activations Density 0.320%

    No Known Activations