INDEX

Explanations

phrases that indicate certainty and consistency over time

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

ÙĪØ§ÙĨ

-0.15

 Rein

-0.15

orz

-0.15

markers

-0.15

cken

-0.14

anh

-0.14

adlo

-0.14

izar

-0.14

ive

-0.14

elize

-0.14

POSITIVE LOGITS

 throughout

0.15

lady

0.15

ovatel

0.15

uese

0.15

andbox

0.15

etur

0.15

ettes

0.14

Until

0.14

|{↵

0.14

etz

0.14

Activations Density 0.116%

phrases that indicate certainty and consistency over time

No Comments

No Known Activations