INDEX

Explanations

words related to specific species and their classifications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

ANDOM

-0.17

 íĭ

-0.17

olio

-0.17

etto

-0.16

ahn

-0.16

expects

-0.15

 fitte

-0.15

åº¦

-0.15

lai

-0.14

uraa

-0.14

POSITIVE LOGITS

ÙĪØ§Ø±

0.16

 å¸¸

0.14

ust

0.14

ut

0.14

 Archives

0.14

iola

0.14

 éĩį

0.14

NM

0.13

WS

0.13

 Bald

0.13

Activations Density 0.014%

words related to specific species and their classifications

No Comments

No Known Activations

words related to specific species and their classifications

No Comments

No Known Activations