INDEX

Explanations

file paths or references to users' directories

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

inese

-0.15

finger

-0.15

ç¯

-0.14

ogue

-0.14

iens

-0.14

resent

-0.14

ç§

-0.14

ipy

-0.13

 parl

-0.13

hoe

-0.13

POSITIVE LOGITS

 McKay

0.15

forma

0.15

ÅĻiv

0.15

uctive

0.14

InputStream

0.14

 Okay

0.14

artin

0.14

thy

0.14

Activations Density 0.014%

file paths or references to users' directories

No Comments

No Known Activations