INDEX

Explanations

keywords related to film, digital effects, and media production

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

ãĤ·ãĥ¼

-0.15

ortal

-0.15

odos

-0.15

oda

-0.14

è§

-0.14

ÎµÎ´

-0.14

orthy

-0.14

esel

-0.14

/stdc

-0.13

yla

-0.13

POSITIVE LOGITS

Slf

0.16

EATURE

0.15

 Stanton

0.15

/Dk

0.15

_accessible

0.15

ÛĮÙĩ

0.15

iani

0.14

alone

0.14

ocale

0.14

AccessException

0.14

Activations Density 0.069%

keywords related to film, digital effects, and media production

No Comments

No Known Activations