INDEX

Explanations

special characters or symbols that may represent significant elements in the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

ģµ

-0.15

.backward

-0.14

_LP

-0.14

indle

-0.14

ikler

-0.13

ä¹¦è®°

-0.13

 recommand

-0.13

 shorts

-0.13

ptal

-0.12

 Tinder

-0.12

POSITIVE LOGITS

or

0.16

 addCriterion

0.15

 analogous

0.15

à¥Įà¤¤

0.15

 compare

0.14

 Peaks

0.14

OffsetTable

0.14

 voluntary

0.14

 alleg

0.14

 analogy

0.14

Activations Density 0.016%

special characters or symbols that may represent significant elements in the text

No Comments

No Known Activations