INDEX

Explanations

locations and geographical references

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

ares

-0.17

inho

-0.15

_WRONG

-0.15

.isNull

-0.14

endon

-0.14

apur

-0.14

eref

-0.14

senal

-0.14

outil

-0.13

PCS

-0.13

POSITIVE LOGITS

Mem

0.21

 Lithuania

0.18

 Baltic

0.17

Nem

0.16

 membr

0.15

 Allen

0.15

ombo

0.15

 Barth

0.15

 Sold

0.15

ilon

0.15

Activations Density 0.011%

locations and geographical references

No Comments

No Known Activations