INDEX

Explanations

terms related to downloading content

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

ophon

-0.15

uer

-0.15

htub

-0.15

cht

-0.14

angu

-0.14

otel

-0.14

ç´°

-0.14

und

-0.13

iling

-0.13

POSITIVE LOGITS

able

0.31

ables

0.25

/stream

0.24

ABLE

0.22

 gratuito

0.20

ers

0.20

ableObject

0.20

/install

0.19

/print

0.19

/upload

0.19

Activations Density 0.019%

terms related to downloading content

No Comments

No Known Activations