INDEX

Explanations

numerical values or time indicators

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

 bois

-0.16

 Courtesy

-0.15

Ø³Ø±

-0.15

 fullPath

-0.15

plr

-0.15

Ð¶ÐµÐ½

-0.14

oba

-0.14

aze

-0.14

 Farrell

-0.14

iguous

-0.14

POSITIVE LOGITS

éĽĦ

0.15

 halde

0.14

_compat

0.14

 Bett

0.14

NULL

0.14

etto

0.14

jedn

0.14

Vog

0.13

arch

0.13

oge

0.13

Activations Density 0.000%

numerical values or time indicators

No Comments

No Known Activations