© 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. 17-LLAMASCOPE-RES-32K
    11. 31821
    Prev
    Next
    INDEX
    Explanations

    terms and concepts related to competition and awards

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    pesan
    -0.14
    émon
    -0.14
     undermin
    -0.13
    conti
    -0.13
    ảy
    -0.12
    apan
    -0.12
     klu
    -0.12
     norge
    -0.12
    ủng
    -0.12
    lse
    -0.12
    POSITIVE LOGITS
    DirectoryName
    0.12
    UnderTest
    0.12
     SaÄŁ
    0.12
    Ctrls
    0.12
    RefPtr
    0.12
    Ä±ÅŁman
    0.12
    διά
    0.12
    @Spring
    0.12
    scoped
    0.11
    _attachments
    0.11
    Activations Density 4.128%

    No Known Activations