INDEX

Explanations

specific terms and identifiers connected to technical specifications and product references

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

iah

-0.15

FAULT

-0.15

lus

-0.15

uce

-0.15

velt

-0.15

-yard

-0.14

yard

-0.14

 YÃĸ

-0.14

 Queen

-0.14

 Arbor

-0.14

POSITIVE LOGITS

odom

0.17

ansas

0.16

 Fischer

0.15

edback

0.15

áº¡n

0.14

ÐµÐ»Ñı

0.14

Ð²Ð¸ÑĤ

0.14

adas

0.14

iegel

0.13

ibold

0.13

Activations Density 0.027%

specific terms and identifiers connected to technical specifications and product references

No Comments

No Known Activations