INDEX

Explanations

phrases related to one-on-one interactions and meetings

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

swick

-0.17

sein

-0.14

PRINTF

-0.14

ç©´

-0.14

anmar

-0.14

lore

-0.13

stor

-0.13

nt

-0.13

teg

-0.13

POSITIVE LOGITS

eters

0.14

sus

0.14

 fashion

0.14

ertz

0.14

/off

0.14

 Ø´Ø¯ÙĨ

0.14

oriously

0.14

manship

0.14

 approach

0.14

Activations Density 0.040%

phrases related to one-on-one interactions and meetings

No Comments

No Known Activations