INDEX

Explanations

file paths and references to file operations in code

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.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

-0.15

erus

-0.14

Ð¾ÑĩÐºÐ¸

-0.14

.dw

-0.14

Î¸Îµ

-0.14

orias

-0.13

.DisplayName

-0.13

dal

-0.13

.SuspendLayout

-0.13

¹

-0.13

POSITIVE LOGITS

atab

0.17

ouce

0.15

 Canter

0.15

oÄŁ

0.14

emony

0.14

ecer

0.14

Ä±rak

0.14

 ÑĢÐµÑģÑĥÑĢ

0.14

ampo

0.14

cases

0.14

Activations Density 0.039%

file paths and references to file operations in code

No Comments

No Known Activations