INDEX

Explanations

specific references to "hazards" or variations of that term

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

lod

-0.16

LOSE

-0.15

isd

-0.15

angs

-0.15

 Pier

-0.14

Arrow

-0.14

perms

-0.14

visited

-0.14

mani

-0.14

 Merrill

-0.14

POSITIVE LOGITS

avery

0.17

orio

0.15

alist

0.15

	Copyright

0.15

ÑĥÑģÐ»Ð¾Ð²

0.14

bart

0.14

omer

0.14

ãĥīãĥ«

0.14

ory

0.14

amed

0.14

Activations Density 0.030%

specific references to "hazards" or variations of that term

No Comments

No Known Activations