© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 19-LLAMASCOPE-RES-32K
    6. 6214
    Prev
    Next
    INDEX
    Explanations

    references to affection or familiarity, particularly in the context of relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    oken
    -0.15
    ropic
    -0.13
    rical
    -0.13
    .INSTANCE
    -0.13
     RaisePropertyChanged
    -0.13
    åª
    -0.13
    441
    -0.13
     Burl
    -0.13
    rias
    -0.13
    .amazon
    -0.13
    POSITIVE LOGITS
     dear
    0.38
    Dear
    0.32
     Dear
    0.30
     fellow
    0.25
     reader
    0.23
     friends
    0.22
    Friends
    0.22
     доÑĢог
    0.21
     ladies
    0.20
     Fellow
    0.20
    Activations Density 0.127%

    No Known Activations