INDEX

Explanations

words related to entertainment or 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 @ 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

olv

-0.17

nota

-0.16

leta

-0.16

 Rubin

-0.16

Ú¯Ø±ÛĮ

-0.15

Vig

-0.15

iffin

-0.14

jad

-0.14

 jurors

-0.14

aca

-0.14

POSITIVE LOGITS

.FontStyle

0.16

pty

0.14

oplay

0.14

stadt

0.14

aise

0.14

HEMA

0.14

 Pied

0.14

linger

0.14

Activations Density 0.000%

words related to entertainment or media content

No Comments

No Known Activations