INDEX

Explanations

forms of the verb "to be."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.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

-0.17

 bird

-0.15

iliary

-0.15

bird

-0.14

Ent

-0.14

entials

-0.14

Dod

-0.14

illas

-0.14

eras

-0.14

eno

-0.14

POSITIVE LOGITS

zens

0.16

apur

0.16

ultz

0.16

.hm

0.15

.fhir

0.15

Vig

0.14

undler

0.14

 Schultz

0.14

burgh

0.14

 Turnbull

0.14

Activations Density 0.207%

forms of the verb "to be."

No Comments

No Known Activations