INDEX

Explanations

questions and statements related to inquiry or investigation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 3-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L3R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.3.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

 credit

-0.16

 Credit

-0.15

Credit

-0.14

ãĥ¼ãĥī

-0.14

à¤®à¤°

-0.14

ÚĺÙĨ

-0.14

poons

-0.14

igor

-0.14

spo

-0.14

gree

-0.14

POSITIVE LOGITS

 Rankings

0.16

bash

0.15

 cock

0.15

adele

0.15

aepernick

0.15

redo

0.15

afs

0.14

 Ukra

0.14

_NC

0.14

Å¯j

0.14

Activations Density 0.059%

questions and statements related to inquiry or investigation

No Comments

No Known Activations