INDEX

Explanations

references to specific locations, particularly related to mountains

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

hydration

-0.15

vak

-0.15

dlg

-0.15

Dlg

-0.15

ardi

-0.14

 linkage

-0.14

ruh

-0.14

.await

-0.14

hog

-0.14

ollar

-0.14

POSITIVE LOGITS

odom

0.17

kre

0.17

Pis

0.15

 Hood

0.15

éĻ°

0.14

quential

0.14

/console

0.14

allen

0.14

ÙĦÙĬÙĦ

0.14

ãĤĤãĤĬ

0.14

Activations Density 0.045%

references to specific locations, particularly related to mountains

No Comments

No Known Activations