INDEX

Explanations

mentions of the word "Telegraph" and its variations

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

ìķħ

-0.17

atus

-0.15

eka

-0.15

éĶĻ

-0.14

rowsable

-0.14

egend

-0.14

 Katz

-0.14

gere

-0.14

erval

-0.14

fred

-0.14

POSITIVE LOGITS

lse

0.17

ottes

0.15

.timeline

0.15

ë³´ëĤ´ê¸°

0.14

ogy

0.14

tron

0.14

Ð¾Ð²Ð¾ÑĢ

0.14

 Emil

0.14

ync

0.14

ycles

0.14

Activations Density 0.001%

mentions of the word "Telegraph" and its variations

No Comments

No Known Activations