INDEX

Explanations

phrases indicating restrictions or conditions regarding links and registrations

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

ÂŃi

-0.16

ÏģÎ¹Î¿

-0.15

thon

-0.15

ked

-0.15

]={↵

-0.14

ANNOT

-0.14

helm

-0.14

.heroku

-0.14

sembly

-0.14

Charsets

-0.14

POSITIVE LOGITS

ait

0.15

ope

0.15

ucci

0.14

nia

0.14

lix

0.14

 actions

0.14

's

0.13

 Britt

0.13

_nb

0.13

Activations Density 0.148%

phrases indicating restrictions or conditions regarding links and registrations

No Comments

No Known Activations