Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 1-LLAMASCOPE-RES-32K
    6. 5930
    Prev
    Next
    INDEX
    Explanations

    references to mental instability or extreme behavior

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 1-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    .scalablytyped
    -0.18
    ãĤ
    -0.15
    errar
    -0.15
     Natural
    -0.14
     helicopt
    -0.14
    irma
    -0.14
    phant
    -0.14
    edia
    -0.14
    aurus
    -0.14
     Offensive
    -0.14
    POSITIVE LOGITS
    .elapsed
    0.15
    leigh
    0.15
    elerik
    0.14
    .instrument
    0.14
    ringe
    0.14
    ccoli
    0.13
    zure
    0.13
    ig
    0.13
    ously
    0.13
     bri
    0.13
    Activations Density 0.016%

    No Known Activations