INDEX

Explanations

occurrences of identifiers and related terminology in a document

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

ora

-0.17

eras

-0.16

otos

-0.16

ORA

-0.15

division

-0.14

lya

-0.14

 elaborate

-0.14

 modern

-0.14

 Mons

-0.14

 Desc

-0.13

POSITIVE LOGITS

iator

0.17

utex

0.16

?f

0.15

ë¥ĺ

0.15

edn

0.15

erif

0.15

eniable

0.15

LLU

0.14

cloak

0.14

/gcc

0.14

Activations Density 0.011%

occurrences of identifiers and related terminology in a document

No Comments

No Known Activations