INDEX

Explanations

statements related to economic indicators and the Federal Reserve's actions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

zych

-0.17

rak

-0.15

ih

-0.14

 Drill

-0.14

umar

-0.14

TabIndex

-0.14

utut

-0.14

 VOID

-0.14

ibi

-0.14

ihn

-0.14

POSITIVE LOGITS

Fed

0.19

stroy

0.17

Fed

0.17

iero

0.16

INES

0.16

fed

0.16

flation

0.15

ormsg

0.15

 infl

0.14

 accommod

0.14

Activations Density 0.021%

statements related to economic indicators and the Federal Reserve's actions

No Comments

No Known Activations