INDEX

Explanations

names, specifically those associated with academic or literary references

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

/Linux

-0.21

éĩı

-0.18

 lifelong

-0.18

aw

-0.16

ady

-0.15

/loading

-0.15

ast

-0.15

les

-0.15

 likeness

-0.15

AKE

-0.15

POSITIVE LOGITS

icrous

0.23

ette

0.19

.parseLong

0.18

urette

0.18

ardo

0.18

erne

0.18

itud

0.18

utenant

0.17

orghini

0.17

raries

0.17

Activations Density 1.160%

names, specifically those associated with academic or literary references

No Comments

No Known Activations