INDEX

Explanations

repetitive phrases emphasizing similarity or sameness

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

 defin

-0.15

oola

-0.15

aro

-0.14

ÄĻd

-0.14

null

-0.14

astle

-0.14

 Kend

-0.14

 null

-0.14

ersed

-0.14

Null

-0.13

POSITIVE LOGITS

odia

0.15

EIF

0.15

abal

0.15

reff

0.15

zp

0.14

Ø§ÙĪØ±ÛĮ

0.14

unami

0.14

 Ø¹Ø±Ø¶

0.14

ãģªãĤī

0.14

CORE

0.14

Activations Density 0.039%

repetitive phrases emphasizing similarity or sameness

No Comments

No Known Activations