INDEX

Explanations

references to semi-structured data or objects, particularly in contexts where semiconductors or similar technologies are discussed

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

uce

-0.15

 semiclass

-0.14

elijke

-0.14

ialis

-0.14

ingham

-0.14

ce

-0.13

ify

-0.13

dw

-0.13

ize

-0.13

POSITIVE LOGITS

umbnail

0.15

.googlecode

0.15

 culo

0.14

buah

0.13

@js

0.13

ltk

0.13

chal

0.13

nock

0.13

ESSAGES

0.13

éĩı

0.13

Activations Density 0.008%

references to semi-structured data or objects, particularly in contexts where semiconductors or similar technologies are discussed

No Comments

No Known Activations