INDEX

Explanations

words associated with historical figures or events

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

orida

-0.18

ogle

-0.17

imuth

-0.15

Ø¬ÙĬÙĦ

-0.15

 meis

-0.14

imitives

-0.14

lÃŃÄį

-0.14

CTL

-0.14

iales

-0.14

ornings

-0.14

POSITIVE LOGITS

 Emin

0.16

iband

0.16

 park

0.15

³

0.15

ãĥ¼ãĥķ

0.15

hut

0.14

Bol

0.14

saida

0.14

rego

0.14

 wood

0.13

Activations Density 0.018%

words associated with historical figures or events

No Comments

No Known Activations