© 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. 11464
    Prev
    Next
    INDEX
    Explanations

    conditional phrases that indicate requests for information or assistance

    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
    ynamodb
    -0.18
     round
    -0.16
    loe
    -0.15
    icana
    -0.15
    esting
    -0.14
    NavController
    -0.14
    ignet
    -0.14
    enties
    -0.14
     ROUND
    -0.13
    687
    -0.13
    POSITIVE LOGITS
    angu
    0.17
    igs
    0.17
    ull
    0.16
     Voll
    0.15
    dale
    0.15
     Mig
    0.14
     Busty
    0.14
    jobs
    0.14
     expo
    0.14
    annis
    0.14
    Activations Density 0.065%

    No Known Activations