INDEX

Explanations

phrases related to locking or securing something

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

oids

-0.15

æĽ²

-0.14

oa

-0.14

lover

-0.14

inha

-0.14

iones

-0.14

coma

-0.14

igua

-0.14

usch

-0.13

Ð»ÑĥÐ³

-0.13

POSITIVE LOGITS

emer

0.17

erner

0.16

allis

0.15

gal

0.15

 Papa

0.15

acias

0.14

ules

0.14

Scripts

0.14

 locking

0.14

ville

0.14

Activations Density 0.023%

phrases related to locking or securing something

No Comments

No Known Activations