INDEX

Explanations

terms related to the spine and spinal health

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

ency

-0.15

oul

-0.15

Hod

-0.14

 pard

-0.14

oulder

-0.14

culate

-0.14

-0.13

Asi

-0.13

 erÃ³t

-0.13

 proven

-0.13

POSITIVE LOGITS

ILING

0.17

(Media

0.15

çĴ

0.15

iling

0.15

inct

0.14

itud

0.14

 Sutton

0.14

Ð¸Ð»Ð¸

0.14

gL

0.14

igers

0.14

Activations Density 0.010%

terms related to the spine and spinal health

No Comments

No Known Activations