INDEX

Explanations

names of companies and organizations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

arro

-0.16

lec

-0.16

Ã³st

-0.15

ãĤ¾

-0.14

SYS

-0.14

Ã¼cken

-0.14

cci

-0.14

animate

-0.14

fo

-0.14

olec

-0.14

POSITIVE LOGITS

ouro

0.17

odont

0.16

ahn

0.15

allel

0.15

0.14

yer

0.14

omial

0.14

Activations Density 0.031%

names of companies and organizations

No Comments

No Known Activations