INDEX

Explanations

phrases indicative of comprehensive analysis or descriptions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

 Idle

-0.16

wahl

-0.15

PPER

-0.15

oci

-0.14

avi

-0.14

hari

-0.14

.opensource

-0.14

 FieldType

-0.13

dens

-0.13

ansen

-0.13

POSITIVE LOGITS

rosso

0.15

ROID

0.14

unny

0.14

ç·

0.14

ONG

0.14

ARA

0.13

_RX

0.13

js

0.13

iod

0.13

ksen

0.13

Activations Density 0.018%

phrases indicative of comprehensive analysis or descriptions

No Comments

No Known Activations