INDEX

Explanations

keywords and key phrases relevant to programming and technical discussions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

udic

-0.17

umping

-0.16

dek

-0.16

eum

-0.15

ral

-0.15

cock

-0.15

asma

-0.14

alle

-0.14

nox

-0.14

oven

-0.14

POSITIVE LOGITS

ãĥ¬ãĥĥãĥĪ

0.15

ellido

0.15

acon

0.15

ullet

0.15

ddy

0.15

 Pond

0.15

imore

0.15

credit

0.14

Äįet

0.14

 credit

0.14

Activations Density 0.187%

keywords and key phrases relevant to programming and technical discussions

No Comments

No Known Activations