INDEX

Explanations

declarations and manipulations related to variables and functions in programming code

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

izr

-0.19

andi

-0.17

 Toro

-0.15

arb

-0.15

dj

-0.14

ATALOG

-0.14

\grid

-0.14

 bergen

-0.14

erb

-0.13

íķľ

-0.13

POSITIVE LOGITS

pekt

0.17

oui

0.14

 Blazers

0.14

aurus

0.14

insk

0.14

hong

0.14

æķ¦

0.14

stav

0.14

umas

0.13

ÑĤÑĸÐ²

0.13

Activations Density 0.014%

declarations and manipulations related to variables and functions in programming code

No Comments

No Known Activations