© 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. 30-LLAMASCOPE-RES-32K
    11. 11538
    Prev
    Next
    INDEX
    Explanations

    discussions around societal dilemmas and existential questions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Were
    -0.17
     Were
    -0.16
    nt
    -0.13
    _ctxt
    -0.13
     opposed
    -0.12
     fueron
    -0.12
    .undefined
    -0.12
     navr
    -0.11
    ieten
    -0.11
    .getBean
    -0.11
    POSITIVE LOGITS
     is
    0.64
     has
    0.58
     isn
    0.47
     can
    0.46
     will
    0.46
     may
    0.43
     seems
    0.42
     appears
    0.41
     hasn
    0.41
     does
    0.40
    Activations Density 10.778%

    No Known Activations