INDEX

Explanations

phrases that specify relationships or clarifications about entities in a context

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

egan

-0.17

-0.16

 Ð¿ÑĢÐ¸Ð²

-0.15

ven

-0.15

linkplain

-0.14

 which

-0.14

pr

-0.14

agna

-0.14

POSITIVE LOGITS

@js

0.16

mrt

0.16

	TokenName

0.15

AtA

0.15

ĶåĽŀ

0.15

etag

0.14

(åľŁ

0.14

ifo

0.14

\E

0.14

Qed

0.14

Activations Density 0.059%

phrases that specify relationships or clarifications about entities in a context

No Comments

No Known Activations