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. 15-LLAMASCOPE-RES-32K
    6. 1950
    Prev
    Next
    INDEX
    Explanations

    words and terms related to music and performance

    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
    -China
    -0.25
     charged
    -0.18
    ãĤĥ
    -0.17
    ottage
    -0.16
    arta
    -0.15
    charged
    -0.15
    chief
    -0.15
    inyin
    -0.15
    channel
    -0.15
    ational
    -0.15
    POSITIVE LOGITS
    lain
    0.23
    abort
    0.19
    reuse
    0.18
    CodeAt
    0.17
    anooga
    0.16
    apeake
    0.15
    soever
    0.15
    pter
    0.15
    ismatic
    0.15
    inks
    0.15
    Activations Density 0.359%

    No Known Activations