INDEX

Explanations

parentheses or round brackets in text

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

 Operations

-0.18

 operations

-0.17

Operations

-0.16

operations

-0.16

Operation

-0.16

endale

-0.16

rr

-0.15

 Operation

-0.15

iedad

-0.15

ALES

-0.14

POSITIVE LOGITS

 Ð´ÐµÑĢ

0.16

iska

0.16

ipple

0.16

ROTO

0.15

à¤¾à¤ĩà¤²

0.15

aub

0.15

ieder

0.15

ÐºÑĥÐ»Ñı

0.15

Tod

0.14

iske

0.14

Activations Density 0.089%

parentheses or round brackets in text

No Comments

No Known Activations