INDEX

Explanations

terms related to concealment or hidden items

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

bags

-0.16

ouch

-0.15

raig

-0.15

ighet

-0.15

edar

-0.14

ÑĢÐ¾Ð¸Ð·

-0.14

ÅĤaw

-0.14

 bags

-0.14

esan

-0.14

getOption

-0.13

POSITIVE LOGITS

 Ø§ÙĦÙħÙĦ

0.14

weathermap

0.14

usic

0.14

 Perr

0.13

ï»¿#

0.13

 Surprise

0.13

ilent

0.13

-window

0.13

ment

0.13

.camel

0.13

Activations Density 0.007%

terms related to concealment or hidden items

No Comments

No Known Activations