© 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. 27-LLAMASCOPE-RES-32K
    11. 2804
    Prev
    Next
    INDEX
    Explanations

    elements related to travel and navigation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.27.hook_resid_post
    Hook Layer
    27
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    atur
    -0.14
    ç¿Ķ
    -0.14
    eldom
    -0.14
    íĤ
    -0.14
    uell
    -0.14
    aroo
    -0.13
    elp
    -0.13
    SOC
    -0.13
    subtotal
    -0.13
    ulum
    -0.13
    POSITIVE LOGITS
     passed
    0.25
     skirt
    0.24
     Emerging
    0.23
     crosses
    0.23
     skirts
    0.23
     passing
    0.22
     ve
    0.22
     emerging
    0.22
     past
    0.22
     Passed
    0.21
    Activations Density 0.060%

    No Known Activations