INDEX

Explanations

references to company names and stock-related terms

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

-0.17

imd

-0.17

anded

-0.17

pad

-0.15

ange

-0.14

ê±°ë¦¬

-0.14

iffe

-0.14

eph

-0.14

POSITIVE LOGITS

 Holding

0.14

UD

0.14

ServletRequest

0.14

 Farrell

0.14

 Neutral

0.14

 Betting

0.14

uddy

0.14

 Brewing

0.14

 Breed

0.14

estroy

0.13

Activations Density 0.030%

references to company names and stock-related terms

No Comments

No Known Activations