© 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. 4-LLAMASCOPE-RES-32K
    11. 4024
    Prev
    Next
    INDEX
    Explanations

    instances of the phrase "go out."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    zk
    -0.15
    ongo
    -0.15
     ActionTypes
    -0.15
    adies
    -0.15
    iner
    -0.15
    abin
    -0.14
    -minus
    -0.14
    osa
    -0.14
    parate
    -0.14
     Ñģобой
    -0.14
    POSITIVE LOGITS
    otes
    0.15
    imation
    0.15
    arkin
    0.14
     force
    0.14
     nÄĥ
    0.14
    ÙħØ©
    0.14
    afia
    0.14
     Kaynak
    0.14
     ëıĮ
    0.14
    ÙħÙĬÙħ
    0.14
    Activations Density 0.012%

    No Known Activations