© 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. 16-LLAMASCOPE-RES-32K
    11. 6033
    Prev
    Next
    INDEX
    Explanations

    expressions of strong emotions or sentiments, particularly happiness and promises

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ฤษ
    -0.15
     Autos
    -0.14
    ants
    -0.14
    oplan
    -0.13
    autos
    -0.13
    APT
    -0.13
    _FATAL
    -0.13
    elder
    -0.13
    iers
    -0.13
     Bryant
    -0.13
    POSITIVE LOGITS
    .Selenium
    0.15
     Ere
    0.13
    stripe
    0.13
    pek
    0.13
     McGill
    0.13
     Cler
    0.13
    orative
    0.13
    Stay
    0.13
     Stay
    0.13
    aling
    0.13
    Activations Density 0.005%

    No Known Activations