INDEX

Explanations

punctuation marks, particularly periods, indicating the end of sentences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ãĥ¼ãĥĨ

-0.17

lest

-0.17

oglob

-0.16

arkin

-0.15

çľī

-0.15

 Gordon

-0.14

obec

-0.14

ÑĥÐ»ÑĮÑĤ

-0.14

alo

-0.14

ulario

-0.14

POSITIVE LOGITS

 Misc

0.15

hani

0.15

cul

0.14

Ã©li

0.14

Factory

0.14

 NOTHING

0.14

unik

0.14

Nothing

0.14

(FALSE

0.14

ï¼

0.14

Activations Density 0.003%

punctuation marks, particularly periods, indicating the end of sentences

No Comments

No Known Activations