INDEX

Explanations

specific identifiers and numerical values related to data or coding 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

 knob

-0.18

 ÑģÐ¾Ñģ

-0.16

ovat

-0.16

ABCDEFGHI

-0.16

urovision

-0.15

ckt

-0.14

Ð¾Ð±ÑĢÐ°Ð·

-0.14

odb

-0.14

å«

-0.14

dri

-0.14

POSITIVE LOGITS

igon

0.16

acle

0.16

ilio

0.15

 Mara

0.15

uti

0.14

urer

0.14

ord

0.14

olk

0.14

aji

0.14

 Malk

0.14

Activations Density 0.045%

specific identifiers and numerical values related to data or coding references

No Comments

No Known Activations