INDEX

Explanations

references to specific food items and ingredients

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

ossier

-0.18

uche

-0.18

rip

-0.16

uese

-0.16

iras

-0.15

ippy

-0.15

ÐµÐ¼Ð¾

-0.14

trys

-0.14

pis

-0.14

CharArray

-0.14

POSITIVE LOGITS

arend

0.16

QA

0.14

cad

0.14

 Penguin

0.13

alah

0.13

asca

0.13

segment

0.13

za

0.13

.inverse

0.13

onth

0.13

Activations Density 0.378%

references to specific food items and ingredients

No Comments

No Known Activations