© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 16-LLAMASCOPE-RES-32K
    6. 629
    Prev
    Next
    INDEX
    Explanations

    negative assessments of behavior and morality

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    esty
    -0.17
    zim
    -0.15
    Ĥ
    -0.14
    inea
    -0.14
    è«
    -0.14
    rious
    -0.14
    ãģłãģij
    -0.14
    arious
    -0.14
    earch
    -0.13
    UNUSED
    -0.13
    POSITIVE LOGITS
     except
    0.61
    except
    0.54
     apart
    0.46
     Except
    0.45
    Except
    0.44
     кÑĢоме
    0.39
    éϤäºĨ
    0.38
     aside
    0.37
    _except
    0.37
    	except
    0.36
    Activations Density 0.273%

    No Known Activations