INDEX

Explanations

attributes of individuals and their dialogues in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

 Says

-0.17

 says

-0.16

says

-0.15

ÅŁi

-0.15

licit

-0.13

 htonl

-0.13

 æĬ

-0.13

ÈĻi

-0.13

 coarse

-0.12

 Ð³Ð¾Ð²Ð¾ÑĢÐ¸ÑĤ

-0.12

POSITIVE LOGITS

 added

0.91

added

0.78

 adds

0.75

Added

0.75

 Added

0.74

 adding

0.72

-added

0.71

add

0.68

 addition

0.68

 Ð´Ð¾Ð±Ð°Ð²

0.66

Activations Density 0.288%

attributes of individuals and their dialogues in various contexts

No Comments

No Known Activations