INDEX

Explanations

time and date references

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

.Formatter

-0.16

LOCKS

-0.16

cro

-0.15

boa

-0.14

 allem

-0.14

umont

-0.14

 Manor

-0.14

tid

-0.14

POSITIVE LOGITS

Ð¼ÐµÐ½

0.17

.nlm

0.16

templ

0.16

ReuseIdentifier

0.15

ãĥ¼ãĥ«

0.15

äºķ

0.15

ãĤ¿ãĥ³

0.15

rog

0.15

oble

0.14

?family

0.14

Activations Density 0.401%

time and date references

No Comments

No Known Activations