INDEX

Explanations

sequences and identifiers related to programming and coding languages

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

ovel

-0.17

oen

-0.16

atel

-0.15

ozor

-0.14

AZE

-0.14

ninger

-0.14

oog

-0.14

 meis

-0.14

ãĤ¹ãĤ«

-0.14

Ð¾Ð¶Ðµ

-0.14

POSITIVE LOGITS

oric

0.16

ado

0.14

/+

0.14

htt

0.14

/-

0.14

ĳ¸

0.14

ÐŀÐł

0.13

ustr

0.13

Activations Density 0.014%

sequences and identifiers related to programming and coding languages

No Comments

No Known Activations