INDEX

Explanations

phrases indicating impact or significance in the context of consequences and relationships

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

 Nicholson

-0.15

vu

-0.15

ãģªãģĹ

-0.15

ULER

-0.15

nea

-0.14

ilestone

-0.14

Ð½ÐµÐ´

-0.14

/on

-0.13

 )↵↵↵↵↵↵↵↵

-0.13

uler

-0.13

POSITIVE LOGITS

atto

0.16

quirrel

0.16

 hunts

0.15

 Hunts

0.15

 seper

0.15

elly

0.14

kf

0.14

avin

0.14

jar

0.14

Activations Density 0.296%

phrases indicating impact or significance in the context of consequences and relationships

No Comments

No Known Activations