© 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. 20682
    Prev
    Next
    INDEX
    Explanations

    instances of recent events or announcements related to political matters

    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
    ấu
    -0.17
    uler
    -0.15
    illion
    -0.15
    YM
    -0.15
    ignKey
    -0.15
    StateMachine
    -0.15
    atis
    -0.14
    nat
    -0.14
    bots
    -0.14
    icum
    -0.13
    POSITIVE LOGITS
    ako
    0.14
    VP
    0.13
     Fork
    0.13
    293
    0.13
    adors
    0.13
    æģµ
    0.13
    jem
    0.13
    ennen
    0.13
    ahr
    0.13
     recently
    0.12
    Activations Density 0.224%

    No Known Activations