INDEX

Explanations

actions that indicate planning or referencing past experiences

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

uggle

-0.16

/documentation

-0.15

evi

-0.15

Zag

-0.14

ARB

-0.14

Ã¢r

-0.14

Ø³Ø§ÙĨÛĮ

-0.14

berger

-0.13

rien

-0.13

ynch

-0.13

POSITIVE LOGITS

ableView

0.16

MD

0.15

EMY

0.14

sole

0.14

isque

0.13

----------------------------------------------------------------------

0.13

ÏĦÎ¹ÎºÎ¿

0.13

-expand

0.13

urma

0.13

Activations Density 0.621%

actions that indicate planning or referencing past experiences

No Comments

No Known Activations

actions that indicate planning or referencing past experiences

No Comments

No Known Activations