INDEX

Explanations

words related to entertainment

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

-0.15

-0.14

roperty

-0.14

reeNode

-0.14

 Blob

-0.13

Äĥng

-0.13

 Gale

-0.13

ives

-0.13

woff

-0.13

POSITIVE LOGITS

anta

0.15

.TestTools

0.14

annis

0.14

SSP

0.14

mma

0.14

annes

0.14

èĥĮ

0.14

itness

0.14

itra

0.13

enha

0.13

Activations Density 0.000%

words related to entertainment

No Comments

No Known Activations