INDEX

Explanations

occurrences of the word "bis."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

rats

-0.16

instr

-0.15

chair

-0.15

atego

-0.15

-0.14

ÐµÐ³Ð¾ÑĢ

-0.14

isl

-0.14

_BLE

-0.14

tail

-0.14

 indeb

-0.13

POSITIVE LOGITS

etz

0.16

 till

0.15

razione

0.15

adh

0.15

enz

0.14

Bonjour

0.14

acher

0.14

erman

0.13

etta

0.13

éĻµ

0.13

Activations Density 0.003%

occurrences of the word "bis."

No Comments

No Known Activations