INDEX

Explanations

phrases indicating the purpose or intended audience for resources or activities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

/J

-0.14

ABCDE

-0.14

	throws

-0.14

Kad

-0.14

ouz

-0.13

quette

-0.13

ajo

-0.13

SZ

-0.13

as

-0.13

ords

-0.13

POSITIVE LOGITS

 neither

0.16

lah

0.15

nah

0.15

edList

0.15

ered

0.14

okens

0.14

ehler

0.14

Ä±lÄ±Ã§

0.14

ç»į

0.14

paged

0.14

Activations Density 0.239%

phrases indicating the purpose or intended audience for resources or activities

No Comments

No Known Activations