© 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. 23-LLAMASCOPE-RES-32K
    11. 11225
    Prev
    Next
    INDEX
    Explanations

    references to freedoms and rights, particularly related to religion and expression

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    lasses
    -0.16
    trail
    -0.16
    ÄįÃŃ
    -0.16
    raith
    -0.14
    }elseif
    -0.14
    avia
    -0.14
    ustum
    -0.14
    stdcall
    -0.14
    ivia
    -0.14
    icrosoft
    -0.14
    POSITIVE LOGITS
     expression
    0.32
     speech
    0.24
     Expression
    0.24
    expression
    0.24
     religion
    0.23
     freely
    0.22
     peaceful
    0.21
    Expression
    0.21
     freedom
    0.21
    -expression
    0.21
    Activations Density 0.031%

    No Known Activations