INDEX

Explanations

concepts and terms related to advice and guidance

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

licht

-0.16

ouver

-0.16

Cin

-0.15

pur

-0.15

ä»£è¡¨

-0.14

onden

-0.14

ove

-0.14

iglia

-0.14

Lite

-0.14

POSITIVE LOGITS

kyt

0.16

 ÑĤÐ²

0.14

 Sphere

0.14

å¡ļ

0.14

omain

0.14

wert

0.14

'gc

0.14

otron

0.14

Sphere

0.14

idlo

0.13

Activations Density 0.023%

concepts and terms related to advice and guidance

No Comments

No Known Activations