Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 24-LLAMASCOPE-RES-32K
    6. 21174
    Prev
    Next
    INDEX
    Explanations

    references to accountability and government actions in relation to societal issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    .jquery
    -0.14
    isten
    -0.14
    654
    -0.14
    omik
    -0.14
    istas
    -0.14
    roup
    -0.13
     Alumni
    -0.13
    ibus
    -0.13
    occupied
    -0.13
    ponent
    -0.13
    POSITIVE LOGITS
     authorities
    0.51
     Authorities
    0.42
     government
    0.42
     governments
    0.40
    Authorities
    0.34
    government
    0.34
    æĶ¿åºľ
    0.33
     Government
    0.31
     officials
    0.30
     governmental
    0.30
    Activations Density 0.314%

    No Known Activations