© 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. 29-LLAMASCOPE-RES-32K
    11. 17656
    Prev
    Next
    INDEX
    Explanations

    instances of the word "finally" and its related forms, indicating moments of realization, completion, or decision-making

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.29.hook_resid_post
    Hook Layer
    29
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     sofort
    -0.19
    Ñĥже
    -0.18
     already
    -0.17
    already
    -0.17
    continued
    -0.17
     już
    -0.16
     bereits
    -0.16
     quickly
    -0.16
    ä¹ħä¹ħ
    -0.16
     okam
    -0.16
    POSITIVE LOGITS
     succ
    0.26
    succ
    0.20
     able
    0.20
     cave
    0.19
     after
    0.17
     admitted
    0.17
     relent
    0.17
     understood
    0.17
     succeeding
    0.17
     Succ
    0.17
    Activations Density 0.083%

    No Known Activations