INDEX

Explanations

phrases and words that indicate questioning, reflection, and evaluation of situations or concepts

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

ãĥĥãĥĦ

-0.16

imately

-0.15

izoph

-0.15

ursors

-0.14

oren

-0.14

irut

-0.14

 Cabinets

-0.14

 introdu

-0.14

 Cabin

-0.14

ĵ

-0.14

POSITIVE LOGITS

amber

0.15

ssf

0.15

amarin

0.15

oldt

0.14

raki

0.14

osg

0.14

etta

0.13

essian

0.13

ypy

0.13

\\.

0.13

Activations Density 0.001%

phrases and words that indicate questioning, reflection, and evaluation of situations or concepts

No Comments

No Known Activations