INDEX

Explanations

gerunds and words related to ongoing actions or processes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 3-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L3R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.3.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

?url

-0.14

Æ°á»Ľ

-0.14

undi

-0.14

rij

-0.13

reece

-0.13

SPATH

-0.13

 Hakk

-0.13

stress

-0.13

 Prim

-0.13

TRACE

-0.13

POSITIVE LOGITS

agua

0.15

Bam

0.14

coni

0.14

.go

0.14

ild

0.14

uby

0.13

adir

0.13

_HEX

0.13

alink

0.13

etri

0.13

Activations Density 0.432%

gerunds and words related to ongoing actions or processes

No Comments

No Known Activations