INDEX

Explanations

quantitative measures or thresholds related to evaluations or specifications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

wagon

-0.15

Precision

-0.14

imat

-0.13

eman

-0.13

nou

-0.13

 Cong

-0.13

 Mort

-0.13

.meta

-0.13

 {?>↵

-0.13

ê³¼ìłķ

-0.13

POSITIVE LOGITS

gnore

0.17

sehen

0.15

ãĤ¹ãĤ¯

0.14

athom

0.14

curity

0.14

ï»¿#

0.14

ccak

0.14

éĽ¶

0.14

AMESPACE

0.14

angu

0.14

Activations Density 0.129%

quantitative measures or thresholds related to evaluations or specifications

No Comments

No Known Activations