INDEX

Explanations

descriptions involving materials or coatings

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

otas

-0.19

asal

-0.18

ignum

-0.17

glomer

-0.16

inspace

-0.16

ahat

-0.15

/false

-0.15

OLUTE

-0.14

adesh

-0.14

olute

-0.14

POSITIVE LOGITS

more

0.15

 prov

0.14

 nothing

0.14

aven

0.14

0.13

ro

0.13

web

0.13

 from

0.13

iest

0.13

Activations Density 0.087%

descriptions involving materials or coatings

No Comments

No Known Activations