INDEX

Explanations

phrases and terms related to various pro-positions or advocacy groups

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

lm

-0.17

alm

-0.16

 Quiet

-0.16

-0.15

lam

-0.15

ild

-0.15

bam

-0.15

ÙĦ

-0.15

 Caps

-0.15

aus

-0.14

POSITIVE LOGITS

PFN

0.17

ìĥī

0.15

usher

0.15

logue

0.14

hlen

0.14

inyin

0.14

errer

0.14

èī²çļĦ

0.14

ARSER

0.14

ModelProperty

0.13

Activations Density 0.012%

phrases and terms related to various pro-positions or advocacy groups

No Comments

No Known Activations