INDEX

Explanations

punctuation marks and syntax elements in code or structured text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.29.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

-0.17

-0.15

ibli

-0.15

lein

-0.15

 placement

-0.15

 Merchant

-0.15

ushman

-0.15

 Placement

-0.15

roe

-0.14

POSITIVE LOGITS

0.26

0.20

ignon

0.16

eness

0.16

ORMAT

0.16

eree

0.16

ensa

0.15

ovit

0.15

ERO

0.15

»

0.15

Activations Density 0.040%

punctuation marks and syntax elements in code or structured text

No Comments

No Known Activations