INDEX

Explanations

concepts that indicate uncertainty or conditional statements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

ajor

-0.17

_managed

-0.16

resher

-0.15

ayet

-0.15

 MILF

-0.14

 Kendall

-0.14

azo

-0.14

ÐĴÐ°Ð¶

-0.14

Roz

-0.14

itori

-0.14

POSITIVE LOGITS

isque

0.16

prm

0.15

pton

0.15

eral

0.15

ãĤ¥

0.14

áº·n

0.14

áºŃu

0.14

apikey

0.14

ecta

0.14

 Advent

0.14

Activations Density 0.005%

concepts that indicate uncertainty or conditional statements

No Comments

No Known Activations