INDEX

Explanations

structured and formal language related to rules and regulations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

pirit

-0.16

ORK

-0.15

à¸Ńà¸ĩ

-0.14

omic

-0.14

itis

-0.13

xml

-0.13

itchen

-0.13

.eql

-0.13

ITY

-0.13

HERE

-0.13

POSITIVE LOGITS

tant

0.16

ingly

0.16

cplusplus

0.15

iros

0.15

ening

0.14

:///

0.14

çļĦæĺ¯

0.14

Ð³Ð°Ð½

0.14

://

0.13

iating

0.13

Activations Density 0.376%

structured and formal language related to rules and regulations

No Comments

No Known Activations