INDEX

Explanations

terms related to structural and spatial attributes in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

utton

-0.15

eyse

-0.15

anza

-0.15

“

-0.14

anta

-0.14

TC

-0.14

TA

-0.14

ëįķ

-0.14

cfg

-0.13

\Column

-0.13

POSITIVE LOGITS

 alike

0.19

bler

0.14

istros

0.14

pare

0.14

Zem

0.14

Î³ÎºÎ¿

0.13

hv

0.13

inou

0.13

/GPL

0.13

_scope

0.13

Activations Density 0.010%

terms related to structural and spatial attributes in various contexts

No Comments

No Known Activations