INDEX

Explanations

mentions of individuals and their actions or experiences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

 kapit

-0.15

Ðĭ

-0.14

vron

-0.14

abbrev

-0.14

.MixedReality

-0.14

ãĤŃãĥ³ãĤ°

-0.14

fold

-0.13

Delegate

-0.13

 Fortune

-0.13

wei

-0.13

POSITIVE LOGITS

aed

0.15

usa

0.14

nat

0.14

ixe

0.14

à¸²à¸«

0.14

 ÐºÑĢÐµÐ¼

0.13

REA

0.13

 Silver

0.13

upil

0.13

REAL

0.13

Activations Density 0.065%

mentions of individuals and their actions or experiences

No Comments

No Known Activations