INDEX

Explanations

references to height, specifically focusing on the term "tall"

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

osos

-0.16

wald

-0.15

å¤ªéĥİ

-0.15

æ£

-0.14

osexual

-0.14

Holy

-0.14

DTD

-0.14

oga

-0.14

illard

-0.14

agedList

-0.13

POSITIVE LOGITS

Ã³r

0.16

ÙĦÙģØ©

0.16

reed

0.15

harma

0.15

.AutoScaleMode

0.15

igit

0.14

ÎµÏĦ

0.14

ustr

0.14

itches

0.14

utions

0.14

Activations Density 0.008%

references to height, specifically focusing on the term "tall"

No Comments

No Known Activations