INDEX

Explanations

numbers and timestamps related to historical events

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

rive

-0.17

tape

-0.17

ysqli

-0.16

serter

-0.15

heimer

-0.15

Ð½Ð¾Ð²

-0.15

taboola

-0.14

.binary

-0.14

agi

-0.14

quist

-0.14

POSITIVE LOGITS

0.16

0.15

ogs

0.15

essel

0.15

0.14

enco

0.14

Ho

0.14

aret

0.14

fo

0.14

Activations Density 0.062%

numbers and timestamps related to historical events

No Comments

No Known Activations