INDEX

Explanations

references to influential individuals or works

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

esian

-0.17

ients

-0.17

isay

-0.16

olean

-0.15

æµ¦

-0.14

artment

-0.14

itan

-0.14

inan

-0.14

avou

-0.13

bilder

-0.13

POSITIVE LOGITS

/power

0.15

_OVERRIDE

0.15

cio

0.14

 Intervention

0.14

bad

0.14

 FindObjectOfType

0.14

arb

0.14

IBUTE

0.14

eve

0.14

åı·

0.13

Activations Density 0.005%

references to influential individuals or works

No Comments

No Known Activations