© 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. 2-LLAMASCOPE-RES-32K
    11. 5573
    Prev
    Next
    INDEX
    Explanations

    mentions of the name "Rosen."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    377
    -0.19
    ssa
    -0.17
    aign
    -0.16
    sher
    -0.14
     Brut
    -0.14
    scan
    -0.14
     Dixon
    -0.14
     Hab
    -0.13
    iker
    -0.13
    seg
    -0.13
    POSITIVE LOGITS
    emez
    0.16
    ho
    0.15
    oyer
    0.15
    eft
    0.15
    lied
    0.15
    piler
    0.15
     tapi
    0.14
    hell
    0.14
    Ø´ÙĨ
    0.14
     hol
    0.14
    Activations Density 0.011%

    No Known Activations