INDEX

Explanations

occurrences of the word "short"

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

 hood

-0.17

GBK

-0.17

è§

-0.14

SSL

-0.14

ORB

-0.14

 Hood

-0.14

 comb

-0.14

POSITIVE LOGITS

onen

0.16

ediator

0.15

isy

0.15

olem

0.15

tron

0.14

ogan

0.14

JNI

0.14

Desk

0.14

oley

0.14

.DEFINE

0.14

Activations Density 0.017%

occurrences of the word "short"

No Comments

No Known Activations