INDEX

Explanations

names and affiliations in an academic context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.29.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

StateManager

-0.16

imeo

-0.16

UILTIN

-0.15

esse

-0.15

uiltin

-0.15

oid

-0.15

avr

-0.14

Longrightarrow

-0.14

quir

-0.14

éģĵ

-0.14

POSITIVE LOGITS

hlen

0.25

ohl

0.23

umuz

0.22

hl

0.22

Nx

0.21

Ink

0.20

Ng

0.20

Bh

0.20

Mg

0.19

Activations Density 0.030%

names and affiliations in an academic context

No Comments

No Known Activations