INDEX

Explanations

terms related to biases in decision-making processes

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

áº§m

-0.15

¼

-0.15

jang

-0.15

rey

-0.14

(())↵

-0.14

rÃ¡l

-0.14

 dignity

-0.13

dff

-0.13

croll

-0.13

POSITIVE LOGITS

 bias

0.59

 Bias

0.51

 biases

0.50

 biased

0.49

bias

0.48

Bias

0.46

_bias

0.43

biased

0.40

åģı

0.38

.bias

0.33

Activations Density 0.234%

terms related to biases in decision-making processes

No Comments

No Known Activations