© 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. 19555
    Prev
    Next
    INDEX
    Explanations

    phrases indicating the absence of something or the act of avoiding unwanted situations

    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
    enef
    -0.15
    etty
    -0.14
    ICODE
    -0.14
     ún
    -0.14
     undecided
    -0.14
    ¡
    -0.14
    opia
    -0.14
    .gwt
    -0.14
     pretty
    -0.14
    ething
    -0.14
    POSITIVE LOGITS
     TOO
    0.20
     risk
    0.19
     alien
    0.18
     resort
    0.18
     necessarily
    0.18
     any
    0.17
     Risk
    0.17
    risk
    0.17
     compromise
    0.16
     sacrifice
    0.16
    Activations Density 0.179%

    No Known Activations