© 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. 4-LLAMASCOPE-RES-32K
    11. 24777
    Prev
    Next
    INDEX
    Explanations

    assertive language and mentions of services or offerings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    openh
    -0.15
    åĢī
    -0.14
    uels
    -0.14
    еÑĢеж
    -0.14
    ofi
    -0.14
    ewis
    -0.14
    stery
    -0.14
    cps
    -0.13
    yaw
    -0.13
    OfDay
    -0.13
    POSITIVE LOGITS
     dul
    0.15
    'gc
    0.15
    kem
    0.14
    assin
    0.14
    -bel
    0.14
    åį´
    0.14
    jem
    0.13
    ĵĺ
    0.13
    é¢ij
    0.13
    _STRUCTURE
    0.13
    Activations Density 0.513%

    No Known Activations