© 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. 7-LLAMASCOPE-RES-32K
    6. 20016
    Prev
    Next
    INDEX
    Explanations

    quantitative data related to experimental conditions and results in a scientific context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    icha
    -0.17
     Lorem
    -0.15
    EI
    -0.15
    cac
    -0.15
    .jasper
    -0.14
    Neo
    -0.14
    pus
    -0.14
    uned
    -0.14
    468
    -0.14
    ssel
    -0.14
    POSITIVE LOGITS
     Werner
    0.16
    eto
    0.15
    ioni
    0.15
    ÙİØ£
    0.15
    oks
    0.15
    idor
    0.14
    illac
    0.14
    HeaderValue
    0.14
    inea
    0.14
    åı£
    0.14
    Activations Density 0.422%

    No Known Activations