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. 21231
    Prev
    Next
    INDEX
    Explanations

    mentions of contributions or contributions to a specific field or context

    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
    arp
    -0.16
    laces
    -0.16
    lace
    -0.16
    ifier
    -0.16
     contributing
    -0.16
    izza
    -0.16
    ify
    -0.15
     contributor
    -0.15
    áy
    -0.15
    stav
    -0.15
    POSITIVE LOGITS
    utory
    0.19
     towards
    0.17
    uting
    0.17
     toward
    0.17
    uters
    0.16
    uter
    0.16
    etto
    0.16
     ÑıÑģ
    0.16
    ansson
    0.16
    alist
    0.16
    Activations Density 0.025%

    No Known Activations