INDEX

Explanations

references to various types of events or issues that are discussed in a general context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

 Morph

-0.17

stown

-0.16

umbo

-0.14

BN

-0.14

 NotSupportedException

-0.14

zenia

-0.14

andalone

-0.13

emos

-0.13

otti

-0.13

 Bless

-0.13

POSITIVE LOGITS

readcr

0.18

aga

0.17

urr

0.16

ãĥ¼ãĥī

0.16

HeaderCode

0.15

iband

0.15

.asc

0.15

isan

0.14

chaft

0.14

 Stock

0.14

Activations Density 0.050%

references to various types of events or issues that are discussed in a general context

No Comments

No Known Activations