INDEX

Explanations

occurences of the letter 'e' in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

ãĥ³ãĥĸ

-0.17

aro

-0.17

Inspectable

-0.15

rne

-0.15

arna

-0.14

abbix

-0.14

Ø³ØªØ§ÙĨ

-0.14

ivative

-0.14

porte

-0.13

çĳŁ

-0.13

POSITIVE LOGITS

chez

0.16

anko

0.15

Ð°Ð½ÐºÐ°

0.15

 Heal

0.14

ubat

0.14

 SOUR

0.14

 Instruments

0.14

ansi

0.14

elt

0.14

bsd

0.13

Activations Density 0.030%

occurences of the letter 'e' in various contexts

No Comments

No Known Activations