INDEX

Explanations

phrases indicating concession or contrast

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

esco

-0.20

rab

-0.16

uler

-0.16

anne

-0.15

 quindi

-0.15

ERC

-0.15

InSeconds

-0.14

hta

-0.14

alc

-0.14

gamber

-0.14

POSITIVE LOGITS

adow

0.15

 share

0.15

ileaks

0.14

gaard

0.14

share

0.14

recio

0.14

adows

0.14

enny

0.14

-share

0.14

arith

0.13

Activations Density 0.011%

phrases indicating concession or contrast

No Comments

No Known Activations