INDEX

Explanations

instances of the word "perhaps."

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

teb

-0.16

zw

-0.16

odb

-0.15

åħħ

-0.14

onte

-0.14

ÑĢÐ¸Ñĩ

-0.14

 Rica

-0.14

æ®Ĭ

-0.14

 beled

-0.13

istrat

-0.13

POSITIVE LOGITS

 engine

0.15

 ignition

0.15

itsu

0.15

cq

0.14

dsl

0.14

pa

0.14

 arasÄ±

0.14

ibo

0.14

å³

0.14

currentColor

0.14

Activations Density 0.181%

instances of the word "perhaps."

No Comments

No Known Activations