INDEX

Explanations

terms related to academic or professional qualifications and affiliations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

acz

-0.15

abi

-0.14

BI

-0.14

ÙĳÙİ

-0.14

 Ø¢Ø´

-0.14

BSP

-0.14

TI

-0.13

hai

-0.13

 Rena

-0.13

cha

-0.13

POSITIVE LOGITS

PTY

0.17

owa

0.15

sWith

0.15

sj

0.14

fault

0.14

.equ

0.14

acht

0.14

umph

0.14

.CustomButton

0.14

[=

0.14

Activations Density 0.015%

terms related to academic or professional qualifications and affiliations

No Comments

No Known Activations