INDEX

Explanations

names and terms associated with specific geographical locations or cultural references

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

uin

-0.21

-0.20

-0.19

er

-0.18

ing

-0.17

ingo

-0.16

an

-0.16

enas

-0.16

aan

-0.16

POSITIVE LOGITS

kers

0.20

à¥įà¤·

0.19

ht

0.17

hr

0.17

nowled

0.17

hti

0.16

shi

0.16

kaar

0.16

nowledge

0.15

.EventQueue

0.15

Activations Density 0.030%

names and terms associated with specific geographical locations or cultural references

No Comments

No Known Activations