INDEX

Explanations

words and phrases related to personal experiences and observations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 21-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L21R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.21.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

Ð¾ÑĤÑĮ

-0.12

 rekl

-0.12

hea

-0.12

.yy

-0.12

alars

-0.12

 eskort

-0.12

_UTF

-0.11

 nÄĽjakÃ½

-0.11

ecome

-0.11

æĮ

-0.11

POSITIVE LOGITS

 beyond

0.13

 surprisingly

0.13

aklÄ±

0.12

 versatility

0.12

 ((((

0.12

 nutshell

0.12

 surprising

0.12

ÃŃrk

0.11

 absolutely

0.11

 simply

0.11

Activations Density 0.016%

words and phrases related to personal experiences and observations

No Comments

No Known Activations