INDEX

Explanations

occurrences of various verbs and adverbs that indicate actions or states relating to necessity and intention

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.19.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

yat

-0.16

ç´Ģ

-0.16

eph

-0.15

ynes

-0.15

yle

-0.15

lings

-0.15

arget

-0.14

just

-0.14

 Cons

-0.14

 Norm

-0.14

POSITIVE LOGITS

idlo

0.18

 CHIP

0.17

CHIP

0.16

qed

0.16

.scalablytyped

0.15

iband

0.15

OTOS

0.15

idth

0.15

 Retrie

0.15

ÑĤÐ¾Ð½

0.15

Activations Density 0.002%

occurrences of various verbs and adverbs that indicate actions or states relating to necessity and intention

No Comments

No Known Activations