INDEX

Explanations

phrases indicating time-related actions and states

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

uet

-0.16

idden

-0.15

 Atlantis

-0.15

ensis

-0.15

iid

-0.15

.Requires

-0.14

Ð½Ð¾Ð¶

-0.14

åīĳ

-0.14

azÄĥ

-0.14

enga

-0.14

POSITIVE LOGITS

.jquery

0.16

 Dome

0.15

angen

0.14

ture

0.14

 dÃ³

0.14

Abb

0.14

 late

0.14

0.13

ekl

0.13

Activations Density 0.052%

phrases indicating time-related actions and states

No Comments

No Known Activations