INDEX

Explanations

references to investigations or oversight of political matters, especially involving Russia

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

vie

-0.16

alc

-0.15

oid

-0.15

 ranger

-0.15

 Ranger

-0.15

ocal

-0.14

argent

-0.14

HECK

-0.14

odor

-0.14

ulp

-0.13

POSITIVE LOGITS

-Trump

0.19

 Manafort

0.19

 Trump

0.19

 Russians

0.18

 Steele

0.18

 Russian

0.18

 Russia

0.17

Russian

0.16

 dirt

0.16

 Campaign

0.16

Activations Density 0.019%

references to investigations or oversight of political matters, especially involving Russia

No Known Activations