INDEX

Explanations

elements related to numerical data or metrics

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

Ã¡y

-0.17

enta

-0.15

áº¯ng

-0.14

ermann

-0.14

STEM

-0.14

leta

-0.14

æ¿

-0.13

ãģĨãģ¡

-0.13

orld

-0.13

olicy

-0.13

POSITIVE LOGITS

IALOG

0.16

è³Ģ

0.14

ruk

0.14

ÐŁÐļ

0.13

oment

0.13

Ã³i

0.13

udit

0.13

 audi

0.13

_RG

0.13

.MM

0.13

Activations Density 0.050%

elements related to numerical data or metrics

No Comments

No Known Activations