INDEX

Explanations

prominent headlines or categories in media content

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

aras

-0.16

fur

-0.16

itest

-0.15

avez

-0.15

 Rough

-0.15

reb

-0.14

PEAT

-0.14

orce

-0.14

_TestCase

-0.14

Reb

-0.14

POSITIVE LOGITS

InMillis

0.15

ãģĹãĤĩãģĨ

0.14

ointments

0.14

lady

0.14

imes

0.14

‘

0.14

HasBeen

0.14

“

0.13

orum

0.13

letters

0.13

Activations Density 0.008%

prominent headlines or categories in media content

No Comments

No Known Activations