INDEX

Explanations

mentions of tips or important pointers for practical tasks

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

 Offline

-0.15

 ActionTypes

-0.14

ite

-0.14

á»ĥn

-0.14

 feast

-0.14

.Selenium

-0.14

uis

-0.14

»

-0.13

abh

-0.13

erb

-0.13

POSITIVE LOGITS

anium

0.17

.Sdk

0.15

ASA

0.15

 Nich

0.14

ocr

0.14

EIF

0.14

ÏĥÏħ

0.14

Activations Density 0.002%

mentions of tips or important pointers for practical tasks

No Comments

No Known Activations