INDEX

Explanations

modal verbs and technical jargon related to actions and processes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.19.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

Suc

-0.15

AMESPACE

-0.15

edar

-0.15

 repet

-0.14

umbo

-0.14

isy

-0.14

kowski

-0.14

 Ð¼Ð½Ð¾Ð³

-0.14

 Celt

-0.14

.Resume

-0.13

POSITIVE LOGITS

odia

0.15

ograd

0.15

roud

0.14

.Gson

0.14

oria

0.14

ITES

0.14

utenberg

0.14

Pub

0.14

PullParser

0.14

ë²ĦìłĦ

0.14

Activations Density 0.001%

modal verbs and technical jargon related to actions and processes

No Comments

No Known Activations