INDEX

Explanations

references to personal information and privacy practices

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

eturn

-0.16

ÑģÑĭÐ»ÐºÐ¸

-0.15

ddit

-0.15

.SDK

-0.15

 Noir

-0.15

.argmax

-0.14

seau

-0.14

mium

-0.14

POSITIVE LOGITS

ANTE

0.19

hest

0.17

ante

0.15

TPL

0.15

 patched

0.14

.INSTANCE

0.14

Jog

0.14

ÑĢÐ°Ñħ

0.14

ÑĤÑĢÐ¾

0.14

Dex

0.13

Activations Density 0.115%

references to personal information and privacy practices

No Comments

No Known Activations