INDEX

Explanations

references to the workplace and work-related contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 3-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L3R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.3.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

iente

-0.16

izes

-0.15

Ð»Ð°Ð¶

-0.15

rganization

-0.15

ëŁ¬

-0.14

 Rights

-0.14

acho

-0.14

ls

-0.14

McA

-0.14

 Manning

-0.14

POSITIVE LOGITS

0.15

0.14

uster

0.14

elsey

0.14

0.13

portion

0.13

isan

0.13

 Alias

0.13

Activations Density 0.007%

references to the workplace and work-related contexts

No Comments

No Known Activations