INDEX

Explanations

terms related to data management and institutional 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

kinci

-0.17

rypton

-0.16

tier

-0.14

æŃ´

-0.14

hm

-0.14

Ã¼re

-0.13

#region

-0.13

Qu

-0.13

pcm

-0.13

_argument

-0.13

POSITIVE LOGITS

dra

0.17

iedade

0.16

oger

0.15

achel

0.15

 Williamson

0.15

 McCoy

0.14

iesel

0.14

hiba

0.14

.mixin

0.14

 typings

0.14

Activations Density 0.025%

terms related to data management and institutional references

No Comments

No Known Activations