INDEX

Explanations

references to caregiving and support services

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

 .↵↵↵↵

-0.15

 &↵

-0.14

/"

-0.14

("

-0.14

/'

-0.13

 _↵↵

-0.13

,âĢ¦↵↵

-0.13

istrovstvÃŃ

-0.13

 ↵↵↵↵

-0.12

,...↵↵

-0.12

POSITIVE LOGITS

:↵

0.77

:↵↵

0.59

:č↵

0.57

 :↵

0.53

0.52

:</

0.48

):↵

0.47

ï¼ļ↵

0.47

:");↵

0.47

:↵↵↵

0.47

Activations Density 0.952%

references to caregiving and support services

No Comments

No Known Activations