© 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. 16468
    Prev
    Next
    INDEX
    Explanations

    phrases that discuss changes in perspective or approach

    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
    alc
    -0.17
     Dien
    -0.16
    iani
    -0.16
    folio
    -0.16
    agli
    -0.15
    cede
    -0.15
     èĪ
    -0.14
    lish
    -0.14
    asp
    -0.14
     Rey
    -0.14
    POSITIVE LOGITS
    ushima
    0.16
    ayacak
    0.15
    obot
    0.15
     обл
    0.15
    ervlet
    0.15
    caa
    0.15
    449
    0.15
     Rider
    0.15
     suppress
    0.14
    Straight
    0.14
    Activations Density 0.732%

    No Known Activations