INDEX

Explanations

key terms related to actions, returns, and changes in context

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

 Prote

-0.15

inel

-0.14

spar

-0.14

obi

-0.14

obel

-0.14

abs

-0.13

ilded

-0.13

kinci

-0.13

brain

-0.13

ÐµÐ»ÐµÐ¹

-0.13

POSITIVE LOGITS

plib

0.16

-urlencoded

0.16

rud

0.15

 endregion

0.14

erson

0.14

Ultra

0.14

ongan

0.14

 æł

0.14

anium

0.14

áº¡t

0.14

Activations Density 0.005%

key terms related to actions, returns, and changes in context

No Comments

No Known Activations