© 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. 9-LLAMASCOPE-RES-32K
    11. 16183
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "Still" as a marker of continuity or contrast

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    eus
    -0.16
    adir
    -0.15
    incident
    -0.15
     Ngh
    -0.15
    AuthProvider
    -0.14
    _AMD
    -0.14
    hydr
    -0.14
    è½®
    -0.14
    zÄħ
    -0.14
    unidad
    -0.13
    POSITIVE LOGITS
    çĦ¶
    0.16
    moth
    0.15
    ness
    0.15
    ington
    0.14
     pagan
    0.14
     pod
    0.14
    cha
    0.14
    od
    0.14
    777
    0.14
    argas
    0.13
    Activations Density 0.011%

    No Known Activations