INDEX

Explanations

phrases that indicate measurements or evaluations of success or performance

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

sert

-0.15

áº¿t

-0.15

'er

-0.15

\Collections

-0.15

ertia

-0.15

ervoir

-0.15

ersh

-0.14

erts

-0.14

 Frankie

-0.14

ivery

-0.14

POSITIVE LOGITS

utsch

0.18

Wak

0.14

imo

0.14

 Kling

0.14

 offsetof

0.14

 Palestin

0.14

:UIAlert

0.14

apter

0.14

 embar

0.14

.quick

0.14

Activations Density 0.014%

phrases that indicate measurements or evaluations of success or performance

No Comments

No Known Activations