INDEX

Explanations

instances of the word "alike" and related expressions indicating similarity or comparison

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.19.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

esters

-0.16

zew

-0.15

ettes

-0.14

ona

-0.14

 overall

-0.14

are

-0.13

stable

-0.13

 exactly

-0.13

overall

-0.13

PRINTF

-0.13

POSITIVE LOGITS

gnore

0.17

mente

0.15

ï¸ı

0.15

licted

0.15

itals

0.14

Ã¼rk

0.14

stride

0.14

quires

0.14

eldo

0.14

lessly

0.13

Activations Density 0.241%

instances of the word "alike" and related expressions indicating similarity or comparison

No Comments

No Known Activations