INDEX

Explanations

instances of "was" and its synonyms that indicate actions or states in historical contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.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

elter

-0.16

annel

-0.16

iska

-0.15

 é¹

-0.15

ething

-0.14

sein

-0.14

thing

-0.14

 Ð½Ð°ÑħÐ¾Ð´

-0.14

Ø¸ÙĬÙģ

-0.14

utorial

-0.14

POSITIVE LOGITS

 instrumental

0.23

 born

0.19

 involved

0.19

 active

0.19

 twice

0.18

 awarded

0.17

 granted

0.17

 Born

0.16

 succeeded

0.16

Activations Density 0.071%

instances of "was" and its synonyms that indicate actions or states in historical contexts

No Comments

No Known Activations