INDEX

Explanations

programming syntax, particularly related to functions and method calls

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

(CC

-0.20

.pp

-0.19

(AF

-0.18

OSC

-0.17

Oc

-0.16

ara

-0.15

.tp

-0.15

IRA

-0.15

 Intercept

-0.15

IDD

-0.14

POSITIVE LOGITS

 å¸

0.15

 Bender

0.15

 Sherman

0.15

 nues

0.14

ugin

0.14

á»ĵng

0.14

inh

0.14

 universally

0.14

azon

0.14

 Feld

0.14

Activations Density 0.057%

programming syntax, particularly related to functions and method calls

No Comments

No Known Activations