© 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. 10-LLAMASCOPE-RES-32K
    11. 9645
    Prev
    Next
    INDEX
    Explanations

    punctuation and question marks in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ordion
    -0.18
    /tos
    -0.17
    onymous
    -0.16
    ìłĪ
    -0.15
    ATAB
    -0.15
    zier
    -0.15
    _Meta
    -0.15
    ajo
    -0.15
    oggle
    -0.14
    lsru
    -0.14
    POSITIVE LOGITS
     Knox
    0.16
     Solo
    0.15
    ificate
    0.14
    acy
    0.14
    atti
    0.14
     Chest
    0.14
     drib
    0.13
    ä¾
    0.13
    602
    0.13
    avar
    0.13
    Activations Density 0.005%

    No Known Activations