INDEX

Explanations

references to roles, titles, and various types of positions in professional contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

rompt

-0.17

htag

-0.16

ÙĪØ«

-0.16

ogen

-0.16

ogens

-0.15

nts

-0.15

\Storage

-0.15

clid

-0.14

cela

-0.14

ield

-0.14

POSITIVE LOGITS

achel

0.18

unga

0.15

cano

0.14

_lua

0.14

kol

0.14

OLT

0.14

 tabs

0.14

ackson

0.14

Os

0.13

acus

0.13

Activations Density 0.029%

references to roles, titles, and various types of positions in professional contexts

No Comments

No Known Activations