INDEX

Explanations

instances of the article "a" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.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

ombo

-0.17

-0.15

ster

-0.15

 vbCrLf

-0.14

åŁĭ

-0.14

unched

-0.14

umer

-0.13

 notice

-0.13

ember

-0.13

POSITIVE LOGITS

imei

0.16

oland

0.15

bilt

0.15

JNI

0.15

onyms

0.15

atoon

0.15

agrams

0.14

_tF

0.13

REC

0.13

auge

0.13

Activations Density 0.413%

instances of the article "a" in various contexts

No Comments

No Known Activations