INDEX

Explanations

punctuation marks, particularly commas

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

uli

-0.18

ilan

-0.16

 Besch

-0.14

ule

-0.14

 Milk

-0.14

chaft

-0.13

imiento

-0.13

Ã´

-0.13

aise

-0.13

bris

-0.13

POSITIVE LOGITS

lam

0.16

0.15

PEG

0.14

Ð»Ð¸ÑĤÐµÐ»ÑĮ

0.14

 Tarif

0.14

finalize

0.14

inth

0.14

çĩŁ

0.14

inta

0.13

Activations Density 0.024%

punctuation marks, particularly commas

No Comments

No Known Activations