INDEX

Explanations

words that indicate conflicts or challenges in understanding or trust

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

ropri

-0.15

oen

-0.15

ako

-0.14

acker

-0.14

åĨĨ

-0.14

.setTimeout

-0.14

otta

-0.14

atto

-0.14

nip

-0.13

izon

-0.13

POSITIVE LOGITS

tility

0.17

ÏĮÎ³

0.15

ħ

0.15

ìļ´ëıĻ

0.15

omore

0.14

unic

0.14

hood

0.14

 Pitch

0.14

 MacDonald

0.13

 decl

0.13

Activations Density 0.025%

words that indicate conflicts or challenges in understanding or trust

No Comments

No Known Activations