INDEX

Explanations

references to technical processes or steps in a system

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

 Tunnel

-0.17

 Tort

-0.16

 Tide

-0.15

Tal

-0.15

 Toll

-0.15

_tunnel

-0.15

Tensor

-0.14

ãĤ¿ãĥ«

-0.14

tolower

-0.14

 Titanic

-0.14

POSITIVE LOGITS

-tr

1.05

tr

0.94

Tr

0.93

_tr

0.92

Tr

0.91

TR

0.88

.tr

0.87

-Tr

0.86

tr

0.84

(tr

0.83

Activations Density 0.203%

references to technical processes or steps in a system

No Comments

No Known Activations