INDEX

Explanations

terms related to decision-making processes and evaluations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

edes

-0.17

ivals

-0.15

-0.14

shal

-0.14

ulers

-0.14

jal

-0.14

funcs

-0.14

uras

-0.13

ow

-0.13

POSITIVE LOGITS

ç³»

0.15

ãĥ¥ãĥ¼

0.14

orno

0.14

aft

0.14

ifer

0.14

stell

0.14

ynn

0.14

 Ø§ÙĦØ¬Ùĩ

0.13

Ð¸ÑĤÐ¸

0.13

ITE

0.13

Activations Density 0.248%

terms related to decision-making processes and evaluations

No Comments

No Known Activations