© 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. 14-LLAMASCOPE-RES-32K
    11. 17156
    Prev
    Next
    INDEX
    Explanations

    phrases related to various forms of abuse and exploitation

    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
    essen
    -0.15
    ubre
    -0.14
     Shield
    -0.14
    ADF
    -0.13
    npos
    -0.13
    crud
    -0.13
     Kürt
    -0.13
    бÑĥ
    -0.13
    abcdefghijklmnop
    -0.13
    atura
    -0.13
    POSITIVE LOGITS
     outright
    0.19
    ifies
    0.15
    /or
    0.15
     Bunny
    0.14
    hole
    0.14
    hol
    0.14
     comm
    0.14
    ovit
    0.14
     hol
    0.14
    aten
    0.13
    Activations Density 0.204%

    No Known Activations