INDEX

Explanations

references to specific systems, structures, and classifications in the context of analysis

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.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

 Mash

-0.15

FAILURE

-0.15

.vn

-0.15

gid

-0.14

ç±³

-0.14

ohan

-0.14

Ð½Ðµ

-0.14

blind

-0.14

mony

-0.14

Au

-0.14

POSITIVE LOGITS

loquent

0.15

erca

0.15

.scalablytyped

0.15

.datatables

0.15

nig

0.14

criptor

0.14

spath

0.14

arken

0.14

 Andrews

0.14

nage

0.14

Activations Density 0.279%

references to specific systems, structures, and classifications in the context of analysis

No Comments

No Known Activations