INDEX

Explanations

phrases that express attempts or efforts to achieve a goal

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

ante

-0.18

tl

-0.16

 Speech

-0.16

locator

-0.15

/locale

-0.15

udic

-0.14

antee

-0.14

 speech

-0.14

ador

-0.14

Locator

-0.14

POSITIVE LOGITS

odash

0.14

.nz

0.14

ayet

0.14

é®®

0.14

]=>

0.14

aspers

0.14

&P

0.13

hardt

0.13

pob

0.13

loo

0.13

Activations Density 0.021%

phrases that express attempts or efforts to achieve a goal

No Comments

No Known Activations