INDEX

Explanations

important nouns and phrases that represent significant concepts or details

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.28.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

hausen

-0.16

nes

-0.16

tek

-0.15

OKEN

-0.15

_INS

-0.14

ingleton

-0.14

.nano

-0.14

ungs

-0.14

iban

-0.13

alan

-0.13

POSITIVE LOGITS

 Zaman

0.16

Reviewer

0.16

 lead

0.16

 other

0.15

 Lead

0.15

 others

0.15

 fellow

0.15

 Fellow

0.15

 Enumeration

0.15

 Others

0.15

Activations Density 0.014%

important nouns and phrases that represent significant concepts or details

No Comments

No Known Activations