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

anter

-0.17

------+------+

-0.16

orsi

-0.14

_ANDROID

-0.14

anes

-0.14

embr

-0.14

Ø§Ø¨Ø§ÙĨ

-0.14

zhou

-0.14

izoph

-0.13

-reset

-0.13

POSITIVE LOGITS

avan

0.17

ç»Ń

0.15

spot

0.15

orra

0.15

rrha

0.14

Ø§Ú©ÛĮ

0.14

inality

0.14

akis

0.14

ilate

0.14

levator

0.14

Activations Density 0.000%

words related to entertainment

No Comments

No Known Activations