INDEX

Explanations

key differences and comparisons between various subjects or entities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

ÅĻi

-0.15

azzi

-0.14

osi

-0.14

á»©ng

-0.14

adin

-0.13

loub

-0.13

eydi

-0.13

 junto

-0.13

zoom

-0.13

ãĤ¤ãĤ¯

-0.12

POSITIVE LOGITS

 difference

1.15

 differences

1.05

difference

1.01

 Difference

1.00

Difference

0.93

 Differences

0.93

 diffÃ©

0.76

å·®

0.74

_difference

0.73

 diferencia

0.70

Activations Density 0.537%

key differences and comparisons between various subjects or entities

No Comments

No Known Activations