INDEX

Explanations

phrases indicating a duration of time, specifically related to multi-year terms or periods

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

aires

-0.18

-0.16

 foss

-0.14

 Ø¨ÙĩØ§

-0.14

ahi

-0.14

Matchers

-0.14

YL

-0.14

Ø§ÙĬØ¯

-0.14

ter

-0.14

isse

-0.14

POSITIVE LOGITS

/latest

0.16

ÐµÐ¿ÑĤÐ¸

0.15

rypt

0.14

-actions

0.14

ÑĢÑİ

0.14

erras

0.14

illis

0.13

ymm

0.13

ABCDE

0.13

uppy

0.13

Activations Density 0.031%

phrases indicating a duration of time, specifically related to multi-year terms or periods

No Comments

No Known Activations