INDEX

Explanations

locations and dates related to events

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

tam

-0.15

 competitive

-0.14

Tam

-0.14

ter

-0.14

 Represent

-0.14

 pass

-0.14

omens

-0.14

 Corner

-0.14

omite

-0.14

 open

-0.14

POSITIVE LOGITS

adium

0.15

andest

0.15

.MixedReality

0.15

reuse

0.15

azon

0.15

 Blowjob

0.14

 personality

0.14

jak

0.14

rios

0.14

etooth

0.14

Activations Density 0.137%

locations and dates related to events

No Comments

No Known Activations