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. 22-LLAMASCOPE-RES-32K
    6. 4532
    Prev
    Next
    INDEX
    Explanations

    words related to cultural references and artistic expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    es
    -0.33
    ez
    -0.24
    esi
    -0.23
    ek
    -0.21
    elter
    -0.21
    esch
    -0.21
    eson
    -0.21
    esk
    -0.20
    esy
    -0.20
    enerator
    -0.19
    POSITIVE LOGITS
    hythm
    0.25
    ama
    0.20
    ricular
    0.19
    aleza
    0.19
    hyth
    0.18
    inha
    0.17
    quoise
    0.17
    prisingly
    0.17
    ri
    0.16
    iously
    0.16
    Activations Density 0.031%

    No Known Activations