INDEX

Explanations

terms related to media production and associated industries

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

Fay

-0.16

 Platt

-0.16

ripp

-0.14

toi

-0.14

 Olymp

-0.13

 Toll

-0.13

orie

-0.13

Ol

-0.13

oles

-0.12

Ã«r

-0.12

POSITIVE LOGITS

ifest

0.17

ivor

0.14

.Undef

0.14

(strtolower

0.14

ynes

0.14

avar

0.13

wide

0.13

urette

0.13

ipline

0.13

Activations Density 0.152%

terms related to media production and associated industries

No Comments

No Known Activations