INDEX

Explanations

key terms related to actions and states, particularly in a constructive context

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

 å¾Ĵ

-0.16

?key

-0.16

ervas

-0.16

uru

-0.16

igmat

-0.15

Neg

-0.14

baugh

-0.14

/ros

-0.14

 lean

-0.14

POSITIVE LOGITS

exp

0.18

elay

0.17

oyer

0.16

.getProperties

0.16

ÑĢÐ¾Ð²Ð¸Ñĩ

0.15

icans

0.14

/cop

0.14

vero

0.14

 Dalton

0.14

berry

0.14

Activations Density 0.001%

key terms related to actions and states, particularly in a constructive context

No Comments

No Known Activations