INDEX

Explanations

dates and occurrences of events

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

esar

-0.17

hrd

-0.16

ucht

-0.15

ento

-0.15

ouch

-0.15

 Ð»Ð¸ÑĨ

-0.15

vet

-0.14

oden

-0.14

 sinh

-0.14

apo

-0.14

POSITIVE LOGITS

erable

0.16

idia

0.15

 Hill

0.15

 taraf

0.14

 Upper

0.14

.syntax

0.14

 Hatch

0.14

EventType

0.14

 hill

0.14

ÐµÑģÑı

0.13

Activations Density 0.052%

dates and occurrences of events

No Comments

No Known Activations