INDEX

Explanations

mentions of specific individuals or organizations

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

owe

-0.16

ingga

-0.15

.TryParse

-0.15

/umd

-0.15

è¡

-0.15

_tA

-0.15

ctest

-0.14

sdk

-0.14

éĻµ

-0.14

POSITIVE LOGITS

seau

0.18

pro

0.17

iral

0.16

pr

0.15

 Ripple

0.15

rain

0.15

 prag

0.15

çıŃ

0.14

 Camden

0.14

mod

0.14

Activations Density 0.046%

mentions of specific individuals or organizations

No Comments

No Known Activations