INDEX

Explanations

phrases related to comparisons and similarities

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

haps

-0.16

tq

-0.15

anja

-0.14

_hz

-0.14

åĭĴ

-0.14

ptic

-0.14

edic

-0.14

uely

-0.13

 Principle

-0.13

OSC

-0.13

POSITIVE LOGITS

ÑģÑĤÐ²Ðµ

0.16

reck

0.15

earn

0.15

essim

0.15

ITEM

0.14

emas

0.14

ÏĩÎ¹

0.14

efon

0.14

stro

0.14

imes

0.14

Activations Density 0.007%

phrases related to comparisons and similarities

No Comments

No Known Activations