INDEX

Explanations

dates and temporal references

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.28.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

 ëħĦëıĦë³Ħ

-0.14

iale

-0.14

amen

-0.14

alo

-0.14

ongo

-0.13

 incor

-0.13

 nearby

-0.13

lore

-0.13

urum

-0.13

.Builder

-0.13

POSITIVE LOGITS

 edition

0.21

 appearance

0.17

 deadline

0.17

 installment

0.17

-through

0.16

deadline

0.16

 instal

0.15

 episode

0.15

avorites

0.14

 segment

0.14

Activations Density 0.030%

dates and temporal references

No Comments

No Known Activations