INDEX

Explanations

references to herbs and botanical elements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

ingly

-0.17

braco

-0.16

Mil

-0.14

oran

-0.14

gis

-0.14

nable

-0.14

lace

-0.14

raci

-0.14

 Courier

-0.14

ÑĪÐµ

-0.14

POSITIVE LOGITS

aceous

0.35

icide

0.24

icides

0.24

/her

0.15

 Concurrent

0.14

ë¥ĺ

0.14

Instant

0.14

aint

0.14

 mortal

0.14

tual

0.13

Activations Density 0.019%

references to herbs and botanical elements

No Comments

No Known Activations