INDEX

Explanations

the presence of the term "ent."

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

omer

-0.16

Khu

-0.15

olid

-0.15

enson

-0.15

.setTo

-0.14

icot

-0.14

WO

-0.14

ically

-0.14

ITED

-0.14

POSITIVE LOGITS

åŀ

0.15

abouts

0.15

 é¦

0.14

riba

0.14

dan

0.14

ader

0.14

rello

0.14

llib

0.13

ï»¿#

0.13

ibs

0.13

Activations Density 0.000%

the presence of the term "ent."

No Comments

No Known Activations