INDEX

Explanations

negation phrases that indicate uncertainty or exceptions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

 Tanks

-0.16

rowned

-0.15

apor

-0.15

mpi

-0.14

umar

-0.14

 zwar

-0.14

htdocs

-0.14

apes

-0.14

appen

-0.14

aska

-0.14

POSITIVE LOGITS

yte

0.16

mo

0.16

rog

0.15

åħ¨éĥ¨

0.15

ClientRect

0.15

 indeed

0.14

 gate

0.14

gad

0.14

elf

0.14

Activations Density 0.043%

negation phrases that indicate uncertainty or exceptions

No Comments

No Known Activations