© 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. 18-LLAMASCOPE-RES-32K
    11. 16259
    Prev
    Next
    INDEX
    Explanations

    mentions of journalists and press freedom issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    kening
    -0.16
    LBL
    -0.15
    resco
    -0.15
    loadModel
    -0.15
     DVD
    -0.14
    ullets
    -0.14
    ldb
    -0.14
    ctors
    -0.13
    leck
    -0.13
    igor
    -0.13
    POSITIVE LOGITS
     Journalism
    0.40
     journalists
    0.40
     journalism
    0.39
     journalist
    0.36
     reporters
    0.33
     journalistic
    0.33
     reporter
    0.30
    journal
    0.29
    _journal
    0.28
     reporting
    0.26
    Activations Density 0.265%

    No Known Activations