INDEX

Explanations

actions involving sending, seeking permission, and general requests

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

 heck

-0.17

asa

-0.16

-0.15

endra

-0.15

lesh

-0.14

ente

-0.14

ents

-0.14

 Jennings

-0.14

inspace

-0.14

OMB

-0.14

POSITIVE LOGITS

æīįèĥ½

0.20

adel

0.16

lef

0.15

ooth

0.14

~>

0.14

holm

0.14

aily

0.14

Ð±ÑĥÐ´ÑĮ

0.14

\xc

0.14

_streams

0.13

Activations Density 0.426%

actions involving sending, seeking permission, and general requests

No Comments

No Known Activations