INDEX

Explanations

references to evaluation standards or criteria

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

oma

-0.15

arro

-0.14

ors

-0.14

(es

-0.14

¥Ĳ

-0.14

SimpleName

-0.13

Lifecycle

-0.13

uos

-0.13

ÑıÑħ

-0.13

POSITIVE LOGITS

erset

0.16

.MixedReality

0.16

Ìģt

0.16

Criterion

0.15

ÐµÑī

0.15

âķĲâķĲ

0.15

abcdefghijklmnop

0.14

igner

0.14

chor

0.14

pressions

0.14

Activations Density 0.009%

references to evaluation standards or criteria

No Comments

No Known Activations