© 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. 5-LLAMASCOPE-RES-32K
    11. 2455
    Prev
    Next
    INDEX
    Explanations

    references to specific policies and individual cases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    IMARY
    -0.17
    iface
    -0.16
    ennent
    -0.16
    ampler
    -0.16
    ORB
    -0.16
    .gs
    -0.15
    代
    -0.15
    erap
    -0.15
    ypi
    -0.14
    senal
    -0.14
    POSITIVE LOGITS
     individual
    0.25
     detail
    0.22
    individual
    0.20
     Individual
    0.20
     details
    0.19
     Detail
    0.19
    ãĥ¼ãĥ³
    0.18
    Individual
    0.18
     Ùģرد
    0.17
    121
    0.17
    Activations Density 0.235%

    No Known Activations