© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 30-LLAMASCOPE-RES-32K
    6. 11015
    Prev
    Next
    INDEX
    Explanations

    mentions of evaluation processes in scientific studies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Published
    -0.15
    Published
    -0.15
    ÑĩаÑģÑĤ
    -0.15
     Lost
    -0.14
    omics
    -0.14
    actics
    -0.14
    Äħż
    -0.14
     wrench
    -0.14
     lost
    -0.13
     Tune
    -0.13
    POSITIVE LOGITS
     examined
    0.55
     studied
    0.48
     evaluated
    0.46
     checked
    0.44
     investigated
    0.44
     analyzed
    0.44
     looked
    0.41
     inspected
    0.41
     assessed
    0.40
     reviewed
    0.40
    Activations Density 0.481%

    No Known Activations