INDEX

Explanations

code syntax or function completion markers

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

atre

-0.16

oph

-0.14

ua

-0.13

Py

-0.13

èį·

-0.13

rel

-0.13

inan

-0.13

 western

-0.12

western

-0.12

quipment

-0.12

POSITIVE LOGITS

EDIA

0.16

tual

0.15

/apis

0.14

 Moody

0.14

ByVersion

0.14

riv

0.14

 Kral

0.14

rive

0.14

).__

0.13

 deutsch

0.13

Activations Density 0.222%

code syntax or function completion markers

No Comments

No Known Activations