INDEX

Explanations

references to legal and procedural terminology

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

lock

-0.17

ARG

-0.16

 Rouge

-0.15

wed

-0.15

 Miles

-0.15

ŀæĢ§

-0.14

ÑĮÐºÐ¾

-0.14

POSITIVE LOGITS

erif

0.20

.fs

0.14

=explode

0.14

icari

0.14

emek

0.14

abbo

0.14

kÃ¼n

0.14

_documento

0.14

ooks

0.14

afort

0.14

Activations Density 0.264%

references to legal and procedural terminology

No Comments

No Known Activations