INDEX

Explanations

negative connotations related to emotional and physical well-being

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

submenu

-0.16

Ùĩ

-0.15

wang

-0.15

 AUTHORS

-0.14

nem

-0.14

Ø±Ùĩ

-0.14

 funk

-0.13

CP

-0.13

licit

-0.13

Ãłu

-0.13

POSITIVE LOGITS

 McCarthy

0.17

ful

0.16

0.15

ultur

0.15

aget

0.14

urer

0.14

Activations Density 0.053%

negative connotations related to emotional and physical well-being

No Comments

No Known Activations