INDEX

Explanations

terms related to mounting and installation processes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

uxt

-0.17

ove

-0.16

ulers

-0.16

alo

-0.15

 Thornton

-0.14

 Grat

-0.14

 Hust

-0.14

afort

-0.14

/request

-0.14

 Britt

-0.14

POSITIVE LOGITS

ioni

0.18

elow

0.17

gom

0.16

uÅ¡

0.16

bar

0.14

fol

0.14

sz

0.14

hardt

0.14

 libertin

0.14

Activations Density 0.020%

terms related to mounting and installation processes

No Comments

No Known Activations