INDEX

Explanations

repetitive phrases that convey a sense of sequence or structure

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

antage

-0.17

ĢìĿ´

-0.17

ÃŃd

-0.15

any

-0.15

lever

-0.14

umn

-0.14

oral

-0.14

onio

-0.14

imeline

-0.14

POSITIVE LOGITS

ãĢħ

0.16

PX

0.15

adera

0.14

runner

0.14

inion

0.13

-none

0.13

ikon

0.13

MouseEvent

0.13

 loosely

0.13

CX

0.13

Activations Density 0.019%

repetitive phrases that convey a sense of sequence or structure

No Comments

No Known Activations