INDEX

Explanations

conditional phrases or contexts that suggest uncertainty or alternatives

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

 HÃ¶

-0.15

.epam

-0.15

-0.14

 Basket

-0.14

yst

-0.14

izr

-0.14

pri

-0.14

lox

-0.14

afort

-0.14

æŃ¯

-0.13

POSITIVE LOGITS

 otherwise

0.23

otherwise

0.20

 Otherwise

0.17

Otherwise

0.15

_MACRO

0.15

amedi

0.15

InputDialog

0.15

vant

0.14

ActionCreators

0.14

 others

0.14

Activations Density 0.101%

conditional phrases or contexts that suggest uncertainty or alternatives

No Comments

No Known Activations