INDEX

Explanations

references to educational qualifications and degrees

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.16.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

 faculty

-0.17

 Faculty

-0.17

 Active

-0.16

gal

-0.15

Faculty

-0.15

oy

-0.15

caf

-0.15

 textbook

-0.15

Ø§ÛĮØ´

-0.14

gal

-0.14

POSITIVE LOGITS

-entry

0.17

completion

0.17

ifetime

0.17

.entry

0.16

 olab

0.15

Ã±ana

0.15

rious

0.15

iÃª

0.15

.LENGTH

0.15

'post

0.15

Activations Density 0.055%

references to educational qualifications and degrees

No Comments

No Known Activations