INDEX

Explanations

specific alphanumeric patterns or strings, possibly relating to identification codes or keys

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

-0.17

iram

-0.15

 Blizzard

-0.15

stm

-0.15

usan

-0.14

eries

-0.14

ayo

-0.14

egov

-0.14

fout

-0.14

ANCELED

-0.13

POSITIVE LOGITS

owell

0.16

ãĥŁãĥ¥

0.15

orious

0.15

ucene

0.14

uci

0.14

ython

0.14

ãĥ³ãĥĸ

0.14

Pocket

0.14

usta

0.14

erts

0.14

Activations Density 0.004%

specific alphanumeric patterns or strings, possibly relating to identification codes or keys

No Comments

No Known Activations