INDEX

Explanations

specific terms related to biological concepts and classifications

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

uche

-0.14

imson

-0.14

 Moran

-0.14

_helpers

-0.13

rack

-0.13

æŃ¯

-0.13

lanma

-0.13

zan

-0.13

ish

-0.13

 Honest

-0.13

POSITIVE LOGITS

éĶĭ

0.16

egasus

0.15

Ð¾Ð½Ð°Ð»ÑĮ

0.15

jeme

0.14

enci

0.14

åĦĢ

0.14

attend

0.14

Void

0.14

åĨĬ

0.14

 attendance

0.14

Activations Density 0.025%

specific terms related to biological concepts and classifications

No Comments

No Known Activations