INDEX

Explanations

distinct markers or identifiers indicating the presence of specialized scientific concepts or terminologies

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

jak

-0.18

ifar

-0.17

oha

-0.15

æ´ĭ

-0.14

iston

-0.14

ãĤ¹ãĤ¯

-0.14

dataGridView

-0.14

ÑģÑĤÑĢÐ¸

-0.14

áº¯p

-0.14

å³¶

-0.14

POSITIVE LOGITS

vern

0.15

 Hanging

0.15

iae

0.15

Center

0.14

icha

0.14

ucle

0.14

olog

0.14

mts

0.14

ear

0.14

Activations Density 0.009%

distinct markers or identifiers indicating the presence of specialized scientific concepts or terminologies

No Comments

No Known Activations