INDEX

Explanations

phrases questioning actions or decisions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

-0.16

less

-0.16

inae

-0.16

setter

-0.15

udos

-0.14

ails

-0.14

ipment

-0.14

AILS

-0.14

xp

-0.14

eum

-0.14

POSITIVE LOGITS

 excess

0.16

 -----------------------------------------------------------------------------↵

0.15

¬¬

0.15

ekce

0.15

 ÑĢÐ°Ð·Ð¼

0.15

AVIS

0.14

BuilderInterface

0.14

mlink

0.14

;;;;;;

0.14

Activations Density 0.140%

phrases questioning actions or decisions

No Comments

No Known Activations