INDEX

Explanations

references to political districts and congressional representation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

fee

-0.17

erson

-0.16

ORIZ

-0.15

heck

-0.14

ĥn

-0.14

punk

-0.14

fee

-0.14

 Statue

-0.14

adel

-0.14

 treatments

-0.13

POSITIVE LOGITS

IntPtr

0.17

'gc

0.15

emos

0.15

ecom

0.14

Ø±ÙĪØª

0.14

è¾

0.14

 æ¼

0.14

ìĤ¬ë¬´

0.14

ë²

0.14

lg

0.14

Activations Density 0.029%

references to political districts and congressional representation

No Comments

No Known Activations