INDEX

Explanations

terms related to unemployment and welfare benefits

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

thouse

-0.18

Ø§Ø¦Ø±

-0.16

íĻ©

-0.16

huy

-0.15

çĽ

-0.15

rawer

-0.14

clud

-0.14

udit

-0.14

Ð´Ð°ÑĤ

-0.14

eah

-0.13

POSITIVE LOGITS

 unemployment

0.27

 unemployed

0.23

_extended

0.18

 taps

0.17

 Temporary

0.17

 sever

0.17

.extensions

0.17

 state

0.16

 Extended

0.16

state

0.16

Activations Density 0.014%

terms related to unemployment and welfare benefits

No Comments

No Known Activations