© 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. 2-LLAMASCOPE-RES-32K
    11. 5574
    Prev
    Next
    INDEX
    Explanations

    instances of summary or concise statements in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    WithDuration
    -0.18
     Niet
    -0.17
    pNet
    -0.15
     SUBSTITUTE
    -0.13
    IMIT
    -0.13
    uber
    -0.13
    伯
    -0.13
     matchmaking
    -0.13
    verse
    -0.13
     ob
    -0.13
    POSITIVE LOGITS
    _nat
    0.17
    enance
    0.16
    ERGE
    0.16
    enton
    0.16
    arnation
    0.15
    ynam
    0.15
    ugar
    0.15
    ckt
    0.15
    ucid
    0.14
    ootball
    0.14
    Activations Density 0.010%

    No Known Activations