INDEX

Explanations

terms related to repair and maintenance activities

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

aea

-0.16

skyt

-0.15

OPS

-0.15

romo

-0.14

reich

-0.14

Ø®Ø·

-0.14

eric

-0.13

/script

-0.13

ymoon

-0.13

ucchini

-0.13

POSITIVE LOGITS

able

0.15

spr

0.15

 Spart

0.14

Pew

0.14

 sprung

0.14

DataTask

0.14

 Reputation

0.14

 beri

0.14

amage

0.14

zilla

0.14

Activations Density 0.017%

terms related to repair and maintenance activities

No Comments

No Known Activations