INDEX

Explanations

terms related to biological processes and classifications in scientific contexts

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

hab

-0.18

ug

-0.17

itters

-0.16

def

-0.14

itter

-0.14

lead

-0.14

les

-0.14

utherland

-0.14

abi

-0.14

ais

-0.13

POSITIVE LOGITS

ä¹ĭä¸Ģ

0.18

ãĥ«ãĤ¯

0.15

="__

0.14

IIIK

0.14

ROUGH

0.14

CEF

0.14

 Amerikan

0.14

âĸį

0.14

Â©Â©

0.14

Activations Density 0.266%

terms related to biological processes and classifications in scientific contexts

No Comments

No Known Activations