INDEX

Explanations

expressions of gratitude and thankfulness

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 3-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L3R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.3.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

enger

-0.16

ildo

-0.16

iren

-0.15

DateFormat

-0.15

oscope

-0.15

crete

-0.14

engan

-0.14

antro

-0.14

isci

-0.14

 beside

-0.14

POSITIVE LOGITS

_parms

0.16

parms

0.15

 JNIEnv

0.15

Į

0.15

iagnostics

0.14

 coquine

0.14

ContextHolder

0.14

elps

0.14

fully

0.14

tparam

0.14

Activations Density 0.010%

expressions of gratitude and thankfulness

No Comments

No Known Activations