INDEX

Explanations

key phrases and terms related to important concepts in documentation or classification

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

afort

-0.19

íĬ

-0.16

ãĥ¬ãĤ¹

-0.16

ertino

-0.16

VISIBLE

-0.15

ipay

-0.15

istrovstvÃŃ

-0.15

å¹¹ç·ļ

-0.14

-eslint

-0.14

skyt

-0.14

POSITIVE LOGITS

0.19

CP

0.16

Cec

0.15

Pocket

0.15

Aw

0.15

ani

0.15

_allocate

0.14

Ø§ÙĪØª

0.14

.enumer

0.14

-p

0.14

Activations Density 0.011%

key phrases and terms related to important concepts in documentation or classification

No Comments

No Known Activations