INDEX

Explanations

references to direction or guidance

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.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

ÐµÐ²Ð¸Ñĩ

-0.18

ICATION

-0.16

ìĬ¤íħĮ

-0.16

íıĲ

-0.16

rish

-0.15

elder

-0.15

omp

-0.15

lum

-0.15

 Grat

-0.15

.Footer

-0.15

POSITIVE LOGITS

 direction

0.23

Direction

0.19

(direction

0.19

 Direction

0.17

direction

0.17

 directions

0.17

-direction

0.17

 toward

0.16

(Direction

0.16

ally

0.16

Activations Density 0.078%

references to direction or guidance

No Comments

No Known Activations