© 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. 30-LLAMASCOPE-RES-32K
    11. 22955
    Prev
    Next
    INDEX
    Explanations

    terms related to oral history and oral communication, particularly in the context of social issues and narratives involving marginalized groups

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    -orange
    -0.21
    -0.19
    agers
    -0.19
    arta
    -0.18
    itchens
    -0.17
    .twig
    -0.16
    ively
    -0.15
    tere
    -0.15
    ility
    -0.15
    emas
    -0.15
    POSITIVE LOGITS
    iginal
    0.23
    ignal
    0.23
    tega
    0.22
    leans
    0.22
    ogonal
    0.21
    ourke
    0.21
    IGIN
    0.20
    loff
    0.20
    ANGE
    0.20
    GAN
    0.19
    Activations Density 0.097%

    No Known Activations