INDEX

Explanations

occurrences of the word "the."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.16.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

-0.18

ling

-0.16

ernes

-0.15

owie

-0.15

ler

-0.14

 role

-0.14

owi

-0.14

 ability

-0.14

ing

-0.14

ìłģ

-0.13

POSITIVE LOGITS

izyon

0.17

PREC

0.14

ailable

0.14

 muit

0.14

many

0.14

 MERCHANTABILITY

0.14

 Ã¶ne

0.14

 many

0.13

 Above

0.13

iline

0.13

Activations Density 0.073%

occurrences of the word "the."

No Comments

No Known Activations