INDEX

Explanations

phrases that introduce contrasting ideas or present factual statements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

inand

-0.14

Ð»Ð°Ð´Ñĥ

-0.13

loub

-0.13

 whom

-0.13

readcr

-0.13

lug

-0.13

CEEDED

-0.12

ija

-0.12

_THAT

-0.12

Î¹Ïİ

-0.12

POSITIVE LOGITS

0.21

,↵↵

0.15

,↵

0.14

ingle

0.14

,↵↵↵

0.14

%#

0.13

 permalink

0.13

,↵↵↵↵

0.13

edio

0.12

à¤¾,

0.12

Activations Density 0.191%

phrases that introduce contrasting ideas or present factual statements

No Comments

No Known Activations