INDEX

Explanations

conditional statements conveying uncertainty or hypothetical scenarios

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

ê·

-0.17

adla

-0.16

/**↵↵

-0.15

HEMA

-0.14

cken

-0.14

annies

-0.14

heimer

-0.14

ÏĦÎµÎ¹

-0.14

.jsp

-0.14

imonial

-0.14

POSITIVE LOGITS

0.19

rames

0.19

 they

0.18

soever

0.17

it

0.17

:↵

0.16

ew

0.16

otope

0.14

 Commercial

0.14

éŃĤ

0.14

Activations Density 0.097%

conditional statements conveying uncertainty or hypothetical scenarios

No Comments

No Known Activations