INDEX

Explanations

references to maintenance-related topics and costs

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

si

-0.17

.getOwnProperty

-0.17

ãĥ«ãĤ¯

-0.16

rlen

-0.15

anners

-0.15

go

-0.15

era

-0.15

ru

-0.15

 sobie

-0.15

Ã«

-0.15

POSITIVE LOGITS

/rest

0.19

ance

0.18

ainer

0.17

ment

0.17

ence

0.17

YPE

0.17

ive

0.16

.Generated

0.16

azar

0.16

Activations Density 0.032%

references to maintenance-related topics and costs

No Comments

No Known Activations