INDEX

Explanations

programming-related queries and actions involving code updates or modifications

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

 Downs

-0.15

icl

-0.15

op

-0.14

ola

-0.14

Hop

-0.14

hos

-0.14

ÏĥÏĥ

-0.14

.hp

-0.14

POSITIVE LOGITS

ÑĢÑĥÑģ

0.16

ìķ½

0.15

CELER

0.14

 explicit

0.14

 explicitly

0.14

ammers

0.14

quares

0.14

ass

0.14

Vien

0.13

íĥľ

0.13

Activations Density 0.087%

programming-related queries and actions involving code updates or modifications

No Comments

No Known Activations