© 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. 22-LLAMASCOPE-RES-32K
    11. 4323
    Prev
    Next
    INDEX
    Explanations

    pros and cons related to a certain topic or product

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     discrepancy
    -0.15
    rif
    -0.15
     discrepancies
    -0.15
    'gc
    -0.14
     defaultMessage
    -0.14
    >NN
    -0.14
    _HINT
    -0.14
    å¸Ń
    -0.14
    avaÅŁ
    -0.14
    untu
    -0.13
    POSITIVE LOGITS
     disadvantages
    0.45
     drawbacks
    0.41
     negatives
    0.39
     downs
    0.38
     downside
    0.38
     disadvantage
    0.36
     cons
    0.36
     limitations
    0.34
     drawback
    0.34
     weaknesses
    0.32
    Activations Density 0.245%

    No Known Activations