© 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. 2-LLAMASCOPE-RES-32K
    11. 2884
    Prev
    Next
    INDEX
    Explanations

    references to scratching or related actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     perc
    -0.17
    Å¡ka
    -0.16
     Hawk
    -0.16
    ropa
    -0.16
    ight
    -0.16
    elda
    -0.15
    Wire
    -0.15
    urm
    -0.15
    Ł³
    -0.15
    uitka
    -0.14
    POSITIVE LOGITS
    scratch
    0.15
    217
    0.15
    817
    0.15
    illation
    0.15
    267
    0.15
    .dtp
    0.14
    apter
    0.14
     Scratch
    0.14
     scratch
    0.14
    0.14
    Activations Density 0.010%

    No Known Activations