INDEX

Explanations

negations and expressions related to honesty and accountability in political discussions

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

iland

-0.16

ourcem

-0.15

fu

-0.15

hya

-0.14

æĢģ

-0.14

ãģĤãĤĬ

-0.14

 Royale

-0.14

Ð°ÑĢÑħ

-0.14

okers

-0.14

eprom

-0.13

POSITIVE LOGITS

 necessarily

0.28

 anymore

0.25

 Ø¨ÙĦÚ©Ùĩ

0.19

 merely

0.19

 sino

0.19

_WP

0.17

 fault

0.16

 Fault

0.16

 actual

0.15

 itself

0.15

Activations Density 0.116%

negations and expressions related to honesty and accountability in political discussions

No Comments

No Known Activations