INDEX

Explanations

references to significant actions or milestones related to progress and development

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

heit

-0.17

nder

-0.16

lage

-0.16

lands

-0.16

 scope

-0.15

erve

-0.15

seed

-0.15

uges

-0.15

lags

-0.14

ongan

-0.14

POSITIVE LOGITS

éª

0.26

 taken

0.24

 Taken

0.23

taken

0.23

 steps

0.23

 Step

0.22

(step

0.21

.step

0.21

step

0.21

 step

0.21

Activations Density 0.024%

references to significant actions or milestones related to progress and development

No Comments

No Known Activations