© 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. 19-LLAMASCOPE-RES-32K
    11. 6071
    Prev
    Next
    INDEX
    Explanations

    specific names or terms related to cultural or artistic references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     NSStringFromClass
    -0.15
    stry
    -0.15
    crow
    -0.15
    SHIP
    -0.15
    ship
    -0.14
    _DLL
    -0.14
    inent
    -0.14
     акÑĤи
    -0.14
    æ´²
    -0.14
    addock
    -0.14
    POSITIVE LOGITS
    .amazonaws
    0.16
    aja
    0.15
    ếu
    0.15
     sche
    0.15
    emaker
    0.14
    owitz
    0.14
    rut
    0.14
     residual
    0.14
    IDER
    0.13
    rij
    0.13
    Activations Density 0.018%

    No Known Activations