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. 24-LLAMASCOPE-RES-32K
    6. 5925
    Prev
    Next
    INDEX
    Explanations

    links and references to academic articles or research studies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ade
    -0.16
    utsch
    -0.15
    enary
    -0.15
    ìĿ´íģ¬
    -0.14
    stag
    -0.14
     keyboards
    -0.14
    guest
    -0.14
    ake
    -0.14
    frey
    -0.14
    áy
    -0.13
    POSITIVE LOGITS
    andbox
    0.16
    داÙħ
    0.16
    itzer
    0.15
    okol
    0.15
    θα
    0.15
    ichick
    0.15
     Bever
    0.14
    PKG
    0.14
    .semantic
    0.14
    ekim
    0.14
    Activations Density 0.004%

    No Known Activations