INDEX

Explanations

nouns related to educational and technological materials or systems

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.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

æĪ¶

-0.15

 transport

-0.14

jsonp

-0.14

hod

-0.14

åłĤ

-0.13

ÏģÎŃÏĢÎµÎ¹

-0.13

latlong

-0.13

yscale

-0.13

 Studios

-0.13

.Skip

-0.13

POSITIVE LOGITS

 supplies

0.17

 prod

0.16

 Stat

0.15

 spir

0.15

ãĥ©ãĤ¹

0.15

 spiral

0.15

wel

0.14

cat

0.14

mlin

0.14

HELL

0.14

Activations Density 0.010%

nouns related to educational and technological materials or systems

No Comments

No Known Activations