INDEX

Explanations

shifts or changes in data or statistics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

iesel

-0.15

luet

-0.15

zier

-0.15

angl

-0.14

à¥Ģà¤£

-0.14

ÏģÏħ

-0.13

ollision

-0.13

Parcelable

-0.13

urope

-0.13

cimal

-0.13

POSITIVE LOGITS

 reverse

0.90

 reversed

0.89

 Reverse

0.82

 reversal

0.81

reverse

0.79

Reverse

0.77

 reversing

0.77

 revers

0.73

_reverse

0.67

 inverse

0.66

Activations Density 0.256%

shifts or changes in data or statistics

No Comments

No Known Activations