© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 14-LLAMASCOPE-RES-32K
    11. 10328
    Prev
    Next
    INDEX
    Explanations

    references to plane incidents and safety concerns

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãĥĨãĥ«
    -0.17
    owie
    -0.15
    ķĮ
    -0.15
     Charges
    -0.15
    flush
    -0.15
     gating
    -0.15
    éĺħ读次æķ°
    -0.15
     Charge
    -0.14
    zcze
    -0.14
     Morgan
    -0.14
    POSITIVE LOGITS
     engine
    0.17
     grounded
    0.16
     McDon
    0.15
     grounding
    0.15
    ras
    0.14
    *pow
    0.14
    AGR
    0.14
     https
    0.14
     dumps
    0.14
     dump
    0.14
    Activations Density 0.025%

    No Known Activations