INDEX

Explanations

references to specific dates and events

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

 Prep

-0.17

aight

-0.17

uhn

-0.15

licative

-0.14

LOPT

-0.14

Ð²ÐµÐ¹

-0.14

á»įt

-0.14

tmpl

-0.14

SError

-0.13

Ð¸ÑĤÑĮ

-0.13

POSITIVE LOGITS

 Dustin

0.15

im

0.15

 hete

0.15

Ãºb

0.14

 unders

0.14

ÏĦÎ¿Ïį

0.14

ÏĥÎ¿Ïħ

0.13

/effects

0.13

abar

0.13

bis

0.13

Activations Density 0.030%

references to specific dates and events

No Comments

No Known Activations