INDEX

Explanations

timestamps and logging information from server or application startup events

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 3-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L3R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.3.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

ostel

-0.14

lico

-0.14

ibo

-0.14

bsolute

-0.14

ILLISE

-0.14

éģ

-0.14

dit

-0.14

kil

-0.13

LETTE

-0.13

èĪ

-0.13

POSITIVE LOGITS

baugh

0.16

acula

0.15

vm

0.15

 Opening

0.15

_UNUSED

0.15

 Simmons

0.15

ertino

0.15

nob

0.15

 opening

0.15

orr

0.15

Activations Density 0.055%

timestamps and logging information from server or application startup events

No Comments

No Known Activations