© 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. 291
    Prev
    Next
    INDEX
    Explanations

    the term "fantasy" along with related concepts in various contexts

    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
     Goodman
    -0.18
    ÑģÑı
    -0.16
    .lucene
    -0.16
    onas
    -0.15
    _patterns
    -0.15
    pattern
    -0.14
    omo
    -0.14
    anzi
    -0.14
    etrics
    -0.14
    /licenses
    -0.13
    POSITIVE LOGITS
    966
    0.16
    CNT
    0.15
    erville
    0.15
    á»ijc
    0.15
     Noble
    0.15
     nob
    0.15
    urity
    0.15
    izr
    0.14
    bilt
    0.14
    ãĥ¬ãĥĥãĥĪ
    0.14
    Activations Density 0.011%

    No Known Activations