INDEX

Explanations

phrases related to achievements and experiences of individuals

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

tam

-0.16

oled

-0.15

 Brace

-0.15

ENN

-0.15

Ã©g

-0.15

egin

-0.14

ADR

-0.14

ÑģÐ¸Ð¼

-0.14

 Garner

-0.14

inem

-0.14

POSITIVE LOGITS

å®Ļ

0.16

 ticking

0.15

 backward

0.14

coil

0.14

Ã¼ss

0.14

 Personal

0.14

backward

0.14

His

0.14

clare

0.13

 blocks

0.13

Activations Density 0.662%

phrases related to achievements and experiences of individuals

No Comments

No Known Activations