© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 25-LLAMASCOPE-RES-32K
    11. 10596
    Prev
    Next
    INDEX
    Explanations

    entities and organizations related to academia and research

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãĤĤãĤĬ
    -0.15
    .circular
    -0.15
    stav
    -0.15
    antor
    -0.14
     commercially
    -0.14
     pam
    -0.14
    marsh
    -0.14
    utas
    -0.14
    otic
    -0.14
    eds
    -0.14
    POSITIVE LOGITS
    (C
    0.14
     Chronicles
    0.14
    .biz
    0.14
     BaÄŁ
    0.14
    .cloudflare
    0.14
    agara
    0.14
    rese
    0.14
    .BorderFactory
    0.14
    ower
    0.13
    ISR
    0.13
    Activations Density 0.315%

    No Known Activations