INDEX

Explanations

occurrences of the article "a" and various numeric values

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 3-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L3R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.3.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

legg

-0.16

NOP

-0.14

ESA

-0.14

Pas

-0.14

ABI

-0.14

spiel

-0.14

_TRANSFORM

-0.14

Bul

-0.13

 meth

-0.13

arem

-0.13

POSITIVE LOGITS

Ion

0.16

iens

0.16

alc

0.15

 Guinea

0.15

ion

0.15

Ion

0.14

ĶĶ

0.14

lon

0.14

_mes

0.14

asser

0.14

Activations Density 0.093%

occurrences of the article "a" and various numeric values

No Comments

No Known Activations