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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 26-LLAMASCOPE-RES-32K
    11. 21749
    Prev
    Next
    INDEX
    Explanations

    keywords related to programming concepts and methods

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 26-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L26R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.26.hook_resid_post
    Hook Layer
    26
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    adox
    -0.15
     ëħĦëıĦë³Ħ
    -0.13
    avax
    -0.13
     -*-č↵
    -0.13
    eld
    -0.13
    auty
    -0.13
     handjob
    -0.13
    èĥ
    -0.13
    ieces
    -0.13
    phan
    -0.13
    POSITIVE LOGITS
     foo
    0.40
     Foo
    0.38
    foo
    0.36
    .foo
    0.35
     some
    0.35
    Foo
    0.35
    /foo
    0.35
     Some
    0.33
     fo
    0.32
     Fo
    0.32
    Activations Density 0.351%

    No Known Activations