INDEX

Explanations

repeated phrases that signify the concept of something being established or in existence

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

fc

-0.16

ally

-0.15

ALLY

-0.15

finder

-0.15

BILE

-0.14

/token

-0.14

Ð¿Ð°

-0.14

fila

-0.13

fld

-0.13

Ð¿ÑĢÐ¸

-0.13

POSITIVE LOGITS

-ÑĤÐ°ÐºÐ¸

0.16

Ú¯ÛĮ

0.16

aneous

0.15

arend

0.14

ĶåĽŀ

0.14

Catch

0.14

è¡Įåĭķ

0.14

ervoir

0.14

uminium

0.14

Activations Density 0.029%

repeated phrases that signify the concept of something being established or in existence

No Comments

No Known Activations