INDEX

Explanations

segments related to programming functions and definitions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

imeo

-0.16

-0.15

ÃŃst

-0.14

astr

-0.14

 Luna

-0.14

hq

-0.14

ouve

-0.14

kou

-0.14

 Late

-0.14

yb

-0.13

POSITIVE LOGITS

grav

0.17

ÏģÏħ

0.16

.shell

0.15

onec

0.15

Hue

0.14

anka

0.14

onet

0.14

avity

0.14

tracts

0.14

hte

0.14

Activations Density 0.005%

segments related to programming functions and definitions

No Comments

No Known Activations