© 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. 25-LLAMASCOPE-RES-32K
    11. 10469
    Prev
    Next
    INDEX
    Explanations

    phrases indicating conditions or qualifications related to statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    isque
    -0.15
    ;x
    -0.15
    celik
    -0.15
    ÄĽl
    -0.15
    allis
    -0.14
     Lauderdale
    -0.14
    lass
    -0.14
    ajs
    -0.13
    ;/
    -0.13
    बल
    -0.13
    POSITIVE LOGITS
    (!
    0.15
    (and
    0.15
    ,is
    0.15
    (?
    0.15
    одо
    0.14
    оÑģÑĤи
    0.14
    ãģªãģĮãĤī
    0.14
    972
    0.13
    !,
    0.13
    ecome
    0.13
    Activations Density 0.098%

    No Known Activations