INDEX

Explanations

proper nouns or identifiers 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 @ 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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

enuity

-0.17

ordum

-0.15

rios

-0.15

æĨ

-0.15

\xaa

-0.14

çľł

-0.14

 Chatt

-0.14

urdu

-0.13

 Cummings

-0.13

oy

-0.13

POSITIVE LOGITS

andler

0.18

ongo

0.17

0.15

gam

0.14

ONGO

0.14

 Romeo

0.14

iens

0.14

 Coordinate

0.14

ainers

0.14

Activations Density 0.486%

proper nouns or identifiers in various contexts

No Comments

No Known Activations