INDEX

Explanations

elements related to data structures and their manipulations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

rosse

-0.18

oni

-0.15

inking

-0.15

ymoon

-0.14

adele

-0.14

#{@

-0.14

Ao

-0.14

addock

-0.14

-0.13

ento

-0.13

POSITIVE LOGITS

'][$

0.19

[$

0.18

[i

0.18

()[

0.18

[(

0.16

 objectAtIndex

0.16

[int

0.16

ÏĮÏģ

0.15

ÑĢÑĥÐ·

0.15

.charAt

0.14

Activations Density 0.143%

elements related to data structures and their manipulations

No Comments

No Known Activations