© 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. 19-LLAMASCOPE-RES-32K
    11. 29808
    Prev
    Next
    INDEX
    Explanations

    phrases related to the concept of "end" or conclusion

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     early
    -0.17
    igen
    -0.17
     outcome
    -0.16
     timing
    -0.15
    jn
    -0.15
    rels
    -0.15
    .fig
    -0.15
     late
    -0.15
    331
    -0.14
     Timing
    -0.14
    POSITIVE LOGITS
    ?url
    0.20
     tunnel
    0.17
     Reach
    0.16
    ãĤ¯ãĥĪ
    0.15
     spectrum
    0.15
     tunnels
    0.15
    _tolerance
    0.14
     nowhere
    0.14
     Tunnel
    0.14
    anza
    0.14
    Activations Density 0.079%

    No Known Activations