INDEX

Explanations

phrases related to comparisons and references

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

 CreateMap

-0.15

âķĹ

-0.15

 Chin

-0.14

ieber

-0.14

 ramps

-0.14

vecs

-0.13

nik

-0.13

ix

-0.13

 intake

-0.13

POSITIVE LOGITS

 divers

0.17

uran

0.15

ptal

0.14

ÏĦÎ±ÏĤ

0.14

hots

0.14

Ø³ØªØ§ÙĨ

0.14

itable

0.13

 VÃ¡c

0.13

OST

0.13

èĢ

0.13

Activations Density 0.003%

phrases related to comparisons and references

No Comments

No Known Activations