INDEX

Explanations

terms associated with headings or titles

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

pel

-0.14

cro

-0.14

indir

-0.13

adin

-0.13

jan

-0.13

ipple

-0.13

cro

-0.13

igid

-0.13

 Cros

-0.13

 mass

-0.13

POSITIVE LOGITS

ogh

0.15

IRD

0.14

emme

0.14

aran

0.14

ÐµÑĢÐµ

0.14

 Bakan

0.14

strup

0.14

 Abbey

0.14

.defaultProps

0.14

Activations Density 0.008%

terms associated with headings or titles

No Comments

No Known Activations