© 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. 15-LLAMASCOPE-RES-32K
    11. 2443
    Prev
    Next
    INDEX
    Explanations

    phrases related to criticism and negative impacts on society

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    unya
    -0.16
    лег
    -0.15
    -runtime
    -0.15
    ToBounds
    -0.14
    StackNavigator
    -0.14
    ingu
    -0.14
    egin
    -0.14
    plex
    -0.14
    osis
    -0.14
     uzman
    -0.14
    POSITIVE LOGITS
     stereotype
    0.21
     stereotypes
    0.17
     bad
    0.17
     stereo
    0.16
     representation
    0.16
    bad
    0.15
     Bad
    0.15
    æĻ´
    0.15
    tere
    0.15
     extremes
    0.15
    Activations Density 0.099%

    No Known Activations