© 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. 2353
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "ka"

    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
    gi
    -0.18
    ya
    -0.16
    shi
    -0.15
    ban
    -0.15
     Haut
    -0.14
    /ts
    -0.14
    crire
    -0.14
    awy
    -0.14
    ando
    -0.14
     fig
    -0.14
    POSITIVE LOGITS
    ovsky
    0.15
    osity
    0.15
    £p
    0.14
    stanov
    0.14
    sted
    0.14
    #
    0.14
    eus
    0.14
    νÏī
    0.14
    ãģĵãĤĵãģ«
    0.13
    lsru
    0.13
    Activations Density 0.020%

    No Known Activations