© 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. 24-LLAMASCOPE-RES-32K
    11. 5540
    Prev
    Next
    INDEX
    Explanations

    instances of the word "directly" and its variations

    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
    richt
    -0.18
     Herc
    -0.14
    εÏģ
    -0.14
    ufact
    -0.14
    uds
    -0.14
    าร
    -0.14
    psc
    -0.14
    ADVERTISEMENT
    -0.14
    impan
    -0.14
    ÐļÐĺ
    -0.14
    POSITIVE LOGITS
     directly
    0.32
    ivity
    0.32
    direct
    0.24
    ives
    0.24
    rices
    0.24
     direct
    0.24
    ivities
    0.24
     Direct
    0.22
    -direct
    0.22
    Direct
    0.21
    Activations Density 0.039%

    No Known Activations