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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 9700
    Prev
    Next
    INDEX
    Explanations

    themes of escape and survival during conflict

    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
    LOB
    -0.17
    iston
    -0.16
    apan
    -0.14
    cip
    -0.14
    à¹Ģà¸Ĺศ
    -0.14
     prisoner
    -0.14
     detain
    -0.14
    queda
    -0.13
     detained
    -0.13
     detainees
    -0.13
    POSITIVE LOGITS
     escape
    0.34
     escaping
    0.27
     refuge
    0.26
     Escape
    0.26
    escape
    0.25
     sanctuary
    0.25
     flee
    0.24
     escapes
    0.24
    Escape
    0.22
     escaped
    0.22
    Activations Density 0.118%

    No Known Activations