© 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. 8-LLAMASCOPE-RES-32K
    11. 1459
    Prev
    Next
    INDEX
    Explanations

    references to boundaries or enclosures, particularly in the context of fences and gates

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 8-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     baiser
    -0.18
    resco
    -0.16
    rrha
    -0.15
    Ế
    -0.15
     æ©
    -0.15
    âķĿ
    -0.15
    -lnd
    -0.15
    صد
    -0.14
     zbyt
    -0.14
    zh
    -0.14
    POSITIVE LOGITS
     net
    0.17
     collo
    0.15
     mur
    0.15
    Æ°á»Ľng
    0.15
     Dos
    0.15
    ature
    0.15
    560
    0.15
    -door
    0.14
    Dos
    0.14
    gate
    0.14
    Activations Density 0.036%

    No Known Activations