INDEX

Explanations

references to specific media formats and file types

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

Ð°ÑĤÐºÐ¾Ð²

-0.16

avirus

-0.16

porn

-0.15

ople

-0.14

asic

-0.14

abbage

-0.14

lider

-0.14

rvine

-0.13

HL

-0.13

mah

-0.13

POSITIVE LOGITS

AKE

0.16

/goto

0.15

 boxed

0.14

.jms

0.14

ÏĥÏĨ

0.13

 diam

0.13

 QAction

0.13

POINT

0.13

«ĺ

0.13

Activations Density 0.032%

references to specific media formats and file types

No Comments

No Known Activations