INDEX

Explanations

references to military service

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 3-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L3R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.3.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

strap

-0.15

 Tower

-0.15

rr

-0.15

OP

-0.14

zim

-0.14

uma

-0.14

hir

-0.14

ship

-0.13

Utf

-0.13

spo

-0.13

POSITIVE LOGITS

ammen

0.17

lernen

0.15

eny

0.15

 backgrounds

0.15

andles

0.15

'gc

0.14

andas

0.14

Ton

0.14

ificio

0.14

ivityManager

0.14

Activations Density 0.033%

references to military service

No Comments

No Known Activations