INDEX

Explanations

occurrences of the verb "been."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

ple

-0.17

 Goldman

-0.15

edii

-0.15

 Bags

-0.14

 bags

-0.14

oud

-0.14

qrt

-0.14

vet

-0.14

IDDEN

-0.14

é»İ

-0.13

POSITIVE LOGITS

alama

0.17

iena

0.16

/cpu

0.15

vise

0.15

edException

0.15

_ALREADY

0.15

ÃŃda

0.14

ypy

0.14

arest

0.14

Ã¤tt

0.14

Activations Density 0.024%

occurrences of the verb "been."

No Comments

No Known Activations