© 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. 16-LLAMASCOPE-RES-32K
    11. 8135
    Prev
    Next
    INDEX
    Explanations

    instances of notable phrases or rhetorical structures in discussions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    xab
    -0.16
    ruba
    -0.16
    iona
    -0.14
     اÙĦصÙĨ
    -0.14
    mdb
    -0.13
    taire
    -0.13
    orks
    -0.13
     Banks
    -0.13
    mans
    -0.13
    ove
    -0.13
    POSITIVE LOGITS
    æ¹¾
    0.17
    ÅĻeh
    0.15
    Inlining
    0.14
    anian
    0.14
     FIXME
    0.14
    indr
    0.14
    rier
    0.14
     weblog
    0.14
    vara
    0.14
    Truthy
    0.14
    Activations Density 0.000%

    No Known Activations