INDEX

Explanations

terms related to application and technical components

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.28.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

veau

-0.18

ÑĮÐµ

-0.17

ÏĩÏĮ

-0.17

emoc

-0.16

ovan

-0.16

_NATIVE

-0.15

utzer

-0.15

ystack

-0.15

STDOUT

-0.14

ulk

-0.14

POSITIVE LOGITS

Inf

0.16

ment

0.16

ÑĨÐµÑĢ

0.16

Inf

0.16

unas

0.16

 Bern

0.16

una

0.15

cel

0.15

ĵ

0.15

 Arthur

0.15

Activations Density 0.030%

terms related to application and technical components

No Comments

No Known Activations