INDEX

Explanations

references to legal and governmental structures

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

íĥĦ

-0.15

acionales

-0.15

reement

-0.14

oden

-0.14

vala

-0.14

ãģıãĤĮ

-0.14

ickerView

-0.14

ntax

-0.14

ereum

-0.14

#endregion

-0.13

POSITIVE LOGITS

anie

0.16

rl

0.15

igr

0.14

ãĥ£

0.14

bb

0.14

isha

0.14

.toolbox

0.14

anych

0.13

borg

0.13

OSC

0.13

Activations Density 0.412%

references to legal and governmental structures

No Comments

No Known Activations