© 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. 24-LLAMASCOPE-RES-32K
    11. 19002
    Prev
    Next
    INDEX
    Explanations

    specific names and locations, particularly focusing on personal names and geographic references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    istrovstvÃŃ
    -0.17
    igger
    -0.16
    orny
    -0.16
    imonial
    -0.15
    haft
    -0.15
    à¥Ģà¤ıम
    -0.14
    itizen
    -0.14
    931
    -0.14
    NotFoundException
    -0.14
    icare
    -0.13
    POSITIVE LOGITS
    enheim
    0.21
    lingen
    0.21
    ingen
    0.20
    heim
    0.17
    ovice
    0.16
    -sur
    0.15
    bourg
    0.15
    trand
    0.15
     Dez
    0.15
    etal
    0.15
    Activations Density 0.123%

    No Known Activations