INDEX

Explanations

phrases related to assistance or support

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 3-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L3R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.3.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

ascii

-0.17

ÑĭÑĪ

-0.16

dojo

-0.15

rome

-0.15

Ð½Ð¸ÑĨÑĮ

-0.15

_into

-0.14

ÃĹ↵↵

-0.14

mlin

-0.14

ushi

-0.14

isz

-0.14

POSITIVE LOGITS

0.16

aidu

0.15

 Peace

0.15

ess

0.15

hin

0.15

-counter

0.15

ÙıÙĩ

0.15

 WINAPI

0.14

Activations Density 0.008%

phrases related to assistance or support

No Comments

No Known Activations