INDEX

Explanations

references to the concept of "living" or "lives."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

velope

-0.15

alf

-0.14

Ø²Ùħ

-0.14

 Runtime

-0.14

 Phonetic

-0.14

ega

-0.14

izont

-0.14

Stmt

-0.14

ToLeft

-0.14

_stmt

-0.13

POSITIVE LOGITS

stone

0.20

LEG

0.19

ston

0.19

pop

0.16

leg

0.16

Leg

0.15

 proof

0.15

obierno

0.15

 breathing

0.15

 Barrett

0.15

Activations Density 0.009%

references to the concept of "living" or "lives."

No Comments

No Known Activations