INDEX

Explanations

phrases related to observations and assessments of situations or issues

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

ĶåĽŀ

-0.15

isu

-0.14

IVA

-0.14

angler

-0.14

éĿ©

-0.14

ÙĦØª

-0.13

weis

-0.13

ãĥ¬ãĥĥãĥĪ

-0.13

FRAME

-0.13

 marrow

-0.13

POSITIVE LOGITS

 cáº£

0.17

ITO

0.16

ito

0.16

_hpp

0.14

 something

0.14

eer

0.14

 specific

0.14

 anything

0.14

èĶ

0.13

.snap

0.13

Activations Density 0.179%

phrases related to observations and assessments of situations or issues

No Comments

No Known Activations