INDEX

Explanations

requests and suggestions related to actions or recommendations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

/epl

-0.16

nte

-0.15

zego

-0.15

éĲ

-0.15

endra

-0.14

mony

-0.14

kus

-0.14

iegel

-0.14

å®

-0.14

à¸ł

-0.13

POSITIVE LOGITS

0.15

uchi

0.15

agra

0.14

 Serialized

0.14

Fault

0.14

upy

0.14

æ¢¯

0.14

_TA

0.14

 Shock

0.13

egt

0.13

Activations Density 0.074%

requests and suggestions related to actions or recommendations

No Comments

No Known Activations