© 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. 5-LLAMASCOPE-RES-32K
    11. 18830
    Prev
    Next
    INDEX
    Explanations

    details related to legal actions or criminal cases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    yw
    -0.17
    286
    -0.17
    apur
    -0.15
     blasted
    -0.15
     pur
    -0.14
     ten
    -0.14
     thr
    -0.14
     unh
    -0.14
    okol
    -0.14
    èİ«
    -0.14
    POSITIVE LOGITS
    uste
    0.15
    é½IJ
    0.15
    atron
    0.14
    render
    0.14
     ez
    0.14
    rong
    0.14
    .dp
    0.14
     пÑĢавда
    0.13
    dsp
    0.13
    esco
    0.13
    Activations Density 0.517%

    No Known Activations