INDEX

Explanations

rankings or placements in various competitive contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

top

-0.19

top

-0.18

erland

-0.17

 topo

-0.17

eron

-0.16

rze

-0.16

_top

-0.16

TOP

-0.15

 tops

-0.15

anz

-0.15

POSITIVE LOGITS

 tier

0.26

-tier

0.26

most

0.25

pling

0.24

flight

0.23

ech

0.23

gross

0.21

-notch

0.21

 dogs

0.21

Tier

0.21

Activations Density 0.027%

rankings or placements in various competitive contexts

No Comments

No Known Activations