INDEX

Explanations

words related to health, safety, and environmental concerns

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.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

rabbit

-0.16

eli

-0.16

Ð±Ð¾ÑĤ

-0.15

 Housing

-0.15

ves

-0.14

Ð´Ð¾Ð²

-0.14

housing

-0.14

longleftrightarrow

-0.14

 Swords

-0.14

ernote

-0.13

POSITIVE LOGITS

oru

0.16

lettes

0.15

ippo

0.15

ledged

0.15

issance

0.15

ÑįÐ¹

0.15

ixo

0.14

ä»ķ

0.14

WebRequest

0.14

.twig

0.13

Activations Density 0.060%

words related to health, safety, and environmental concerns

No Comments

No Known Activations