INDEX

Explanations

academic degrees and programs

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

acent

-0.18

andest

-0.18

hap

-0.16

ICIENT

-0.15

avic

-0.15

èĪĪ

-0.15

/*č↵

-0.15

self

-0.14

licht

-0.14

iterals

-0.14

POSITIVE LOGITS

 degree

0.20

cum

0.18

 candidate

0.17

-animate

0.17

 honor

0.17

 magna

0.17

-degree

0.17

0.16

 candidates

0.16

/B

0.16

Activations Density 0.014%

academic degrees and programs

No Comments

No Known Activations