INDEX

Explanations

references to the name "Nehru" and its variations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

mpl

-0.18

eward

-0.16

ahren

-0.16

kus

-0.15

brook

-0.15

LAY

-0.14

conti

-0.14

ãĤ¤ãĤ¯

-0.14

æľį

-0.14

ToWorld

-0.14

POSITIVE LOGITS

emiah

0.24

Neh

0.21

theless

0.18

CESS

0.17

ccess

0.16

laces

0.16

dle

0.16

ropolis

0.15

anyahu

0.15

-Nazi

0.15

Activations Density 0.027%

references to the name "Nehru" and its variations

No Comments

No Known Activations